Knowledge Management & E-Learning: An International Journal, Vol.2, No.4.


Analysing the Relationship between Learning Styles and Navigation Behaviour in Web-Based Educational System Nabila Bousbia*
LMCI, Ecole nationale Supérieure d'Informatique (ESI) BP 68M, 16270, Oued-Smar, Algiers, Algeria E-mail:

Issam Rebaï
Telecom Bretagne, Computer Science Department Technopôle Brest-Iroise, CS 83818 29238, Brest cedex 3, France E-mail:

Jean-Marc Labat
LIP6, Laboratoire de Paris 6 104, Avenue du Président Kennedy, 75016, Paris, France E-mail:

Amar Balla
LMCI, Ecole nationale Supérieure d'Informatique (ESI) BP 68M, 16270, Oued-Smar, Algiers, Algeria E-mail: *Corresponding author
Abstract: The aim of our research is to automatically deduce the learning style from the analysis of browsing behaviour. To find how to deduce the learning style, we are investigating, in this paper, the relationships between the learner‟s navigation behaviour and his/her learning style in web-based learning. To explore this relation, we carried out an experiment with 27 students of computer science at the engineering school (ESI-Algeria). The students used a hypermedia course on an e-learning platform. The learners‟ navigation behaviour is evaluated using a navigation type indicator that we propose and calculate based on trace analysis. The findings are presented with regard to the learning styles measured using the Index of Learning Styles by (Felder and Solomon 1996). We conclude with a discussion of these results. Keywords: Learning style, navigation behaviour, trace analysis. Biographical notes: Nabila Bousbia received the M.S. degree in Computer Science from the School of Computer Science (ESI), Algeria, in 2005. She is now a lecturer there. She is pursuing a Ph.D degree in Computer Science under a joint supervision of ESI, Algeria, and Paris 6 University, France. Her research interests include trace analysis, user modelling and learning styles.

Knowledge Management & E-Learning: An International Journal, Vol.2, No.4.
Issam Rebaï is an associate professor in the Department of Computer Science at Telecom Bretagne Engineering School in France. He received his Ph.D. from the University of Paris, Descartes, in 2006. His dissertation focused on the design and the development of a platform allowing the capitalization of software components for interactive learning environments. He then joined the CNRS in 2008 as a postdoctoral fellow at the LIMSI Computer Science Laboratory. He conducted research on ambient environments, emotions, and robotics. His research interests include learning metadata, affective and ubiquitous computing. Jean-Marc Labat is full Professor in computer science at Paris6 University. He is head of a research team within the Lip6 laboratory and leads the UTES, a university joint service. He is the current president of the ATIEF association. His research focuses generally on cognitive modelling of user experiencing problem solving. His current research goals are to investigate serious games. Amar Balla received the Ph.D. degree on Computer Science from the School of Computer Science (ESI), Algeria, in 2005; and then a clearance to conduct research. He is head of a research team within the LMCS laboratory and leads a department at the ESI School. His research interests mainly focus on adaptative hypermedia and student modelling.


1. Introduction
The use of computers in education brings new opportunities, every day. Research in this field, or more generally in the field of learner modelling, was focused mainly on detecting features related to the learner‟s knowledge, interests, goals, backgroun d, and individual traits (Brusilovsky and Millán 2007). We are interested in this last aspect, in particular in the learning style. Learning styles refer to how individuals prefer to organize and represent information (Reed and Oughton 1997). The learning style is thus connected to both a set of behaviours - strategies in the way of managing and organizing the information, as well as the way of implementing these behaviours and strategies. Thus, several studies on Educational Hypermedia Systems (EHS) have used learning styles (LS), these last years, as a criterion for adaptation and tracking to improve the learning results. In fact, the integration of this theory in a computer environment allows us to consider the learning style of each learner individually, by adapting the content, in terms of form, structure, presentation order of learning activities and choices of these activities, which is a difficult or impossible task for the teacher in a traditional training situation with a group or a class of learners. However, given the variety of definitions of the learning style concept, several learning style models were proposed in the literature (over 70 according to Coffield and al. (2004)). Some of them were implemented in educational hypermedia systems (WHURLE, CS383, ILASH, etc. (Brown et al. 2005)). The detection of these styles rests on questionnaires proposed for each model (ILS (Felder and Solomon 1996), LSQ (Honey and Mumford 1992), etc.). Our interest concerns the automatic detection of learning styles, in a web-based learning, by the analysis of the learner‟s behaviour through the collection and the interpretation of traces on the learner‟s activities.

N." The learning style is thus connected to both a set of behaviours . we first describe the learning style theory and its implementation in educational hypermedia systems (EHS). Learning Style Cognitive psychology has long focused on individual differences and their impact on learning (Ayersman and von Minden. In this paper. Liu and Reed. For example. and the learning process (experiential. namely preferences (sensory or environment). various theories of learning styles have been developed with an increasing frequency during the last decades. 2005).). Background 2. Section 7 finally concludes the paper. In this way. (2000). data processing. To have an overview of these different theories. a simple reference to the literature highlights the plurality and the diversity of definitions. but also to individual differences that can be found in the psychology of intelligence or personality. the aim of this paper is to examine the relationships between the learning styles and the learner‟s navigation behaviour in a web-based learning environment. In Section 3.strategies in the way of managing and organizing the information. learning strategy. They are largely based on the Curry‟s „onion‟ model (Curry 1983). or (iii) personality characteristics. 1994). research was directed towards the concept of "learning style" relating to the individual‟s learning preferences (Brusilovsky and Millán 2007). Chevrier et al. predisposition. Section 5 details and discusses the results to point out some guidelines to deduce the learning styles from trace analysis. A definition gathering these three aspects is given by Riding and Rayner (2001): "The expression learning style refers to a set of individual differences. researchers like DeBello (1990). „cognitive style‟ and „information processing style‟ are all terms that have been used interchangeably by various researchers. the terms „learning style‟. there is also a wealth of confusing terminology (Brown et al. (2004) identified 71 models.1. We propose to use observable indicators describing the navigation behaviour through a navigation typology. set typologies or categorizations of these models by identifying the different dimensions of the learning style. Section 4 presents the methodology of the experiment. 1995. In search of practical means to respect these differences. Riding and Rayner (2001). et al. etc. (2004). as well as the way of implementing these behaviours and strategies. which include not only an expressed personal preference concerning teaching or an association with a particular form of learning activity.402 Bousbia. Coffield et al. the cognitive ability / personality. In addition to this vast collection of learning style theories. Cassidy (2003) and Coffield et al. The term „learning style‟ has been used in this paper as an overarching term that is meant to include any psychological or . according to whether they refer to: (i) a specific way of behaving. Chevrier et al. The analysis of some classifications leads us to say that they all try to distinguish the three elements of definitions. we explain our approach to deduce the learning style from behavioural indicators. or preferences related to learning and teaching contexts. To address this issue. mainly due to their particular position concerning whether learning styles are stable or not over time. However. 2. in order to provide information that can be used in the detection process. (2000) organize them within three categories. (ii) information processing. To clarify this concept.

as (Sangineto et al.Knowledge Management & E-Learning: An International Journal. how can these theories be then used in hypermedia learning environments? The studies presented by the authors of EHS indicate a positive influence of use of learning styles in such hypermedia learning environment (Carver et al. We also consider that it is flexibly stable according to the situations and the context. The majority of these EHS take only one learning style model into account. although other models may have stronger theoretical foundations. No. the existing systems generally ask learners to complete a psychological questionnaire. 2007) noted. FSLSM was widely experimented and validated on an engineering student population. (ii) the model should display a good degree of validity and reliability/internal consistency (and thus provide accurate evaluations of learning style). 2006).g.2. the one proposed by the authors of the LS model (e. (Wang et al. we have chosen to use FSLSM in our experiment. Learning Style and EHS In the specific context of online learning. including learning styles satisfying a set of conditions. 2007) construct a model from the various existing LS models. 2003). presented in the coming sections. (v) the model should be easily administered to university students. no model of learning style has been proposed to inform on how learners work with digital resources. (iii) the model should be suitable for use with an adaptive web-based educational system. how can we differentiate these learning styles? For the LS identification. 2000). Other systems require from learners to explicitly express their learning styles at the beginning of the course. are conceived for traditional face-to-face educational settings. Our work joins these studies that propose a learning style model from the existing ones. have been proposed. based on existing ones. research on learning styles (LS) is still in a preliminary and exploratory stage (Brusilovsky and Millán 2007). except in some systems where the update is directly activated by the student or activated . (Triantafillou et al.4. 2008). Thus. not for computer-mediated instruction (Popescu 2009). However. Felder and Silverman‟s model (Felder and Silverman 1988) remains the most widely used. For all these reasons. 2005). who justify their choice for FSLSM with the fact that it fulfils most of the required criteria: (i) the model should be able to quantify learning styles (and hence model them computationally). 2003). 2007). Moreover. The overall objective of the use of learning styles in such a context is the adaptation and customization of learning. Index of Learning Style (ILS) (Felder and Solomon 1996) of the FSLSM). the current EHS use some existing learning style models from those considered as the most popular. 403 educational model used in research into cognitive processes applied to a learning situation. FSLSM contains useful pragmatic recommendations to customize teaching according to the students‟ profiles (Popescu 2008). or a portion of its dimensions or preferences. it should be noted that most learning style theories. 2. Furthermore. In terms of used LS model. the detection of the learning style. allows learning individualization and its improvement through the discovery of learner‟s preferred learning strategies as well as the adapted situations and teaching (Chevrier et al. iv) the model should be suitable for use with multimedia. 1999) (Papanikolaou et al.2. which is usually not updated. in (Popescu 2008). The reasons behind its popularity are summarized by (Brown et al. (Sangineto et al. Consequently. Therefore. Indeed. (Popescu et al. The result is stored in the learner model. attempts to design learning style models for EHS. So. the authors suggest creating a classification of LS that can be used with a learner model by adding layers to the Curry‟s model. Vol. In (Brown et al. proposed in psychology literature.

questionnaires. 2. as Rich (1999) pointed out. Learners are therefore classified as stereotypes. Cristea. (Chan-Lin 1998). in the next section. iWeaver (Wolf 2007). DeLeS (Graf 2007). 2008). However. Indeed. this approach would raise new issues. N. Learning Style on the Web In order to examine the relationships between learning styles and learners‟ behaviour on hypermedia. and (Marrison and Frick 1994) have focused on this aspect. et al. several new approaches propose to identify and / or update the learning styles based on behaviour analysis (e. as a tool for identifying learning styles. several studies suggest that learners with field independent style could particularly benefit from the choice of media (text.3. and how to update its values? To answer this question. The learning style model proposed by (Witkin et al. education and computer science have been conducted. the stability of learning styles is still a controversial issue. the use. animation. particularly in terms of format. As soon as learning styles change. using questionnaires for identifying learning styles underlies the assumption that the learning styles are stable for a long period of time. (Chang. which is the aim of our study. of questionnaires. However. Stash. Secondly. Paredes and Rodrí guez 2004). accessibility. in general. Moreover. we explore studies on the relationships between learning styles and the learner‟s behaviour on the Web. the assumption is made that students are motivated to fill out the questionnaire properly and to the best of their knowledge about their preferences. However. voice). as discussed before. 1971) (field dependence or independence) has been the most studied. The work of (Ghinea and Chen 2003) also states that they prefer . we are particularly interested in web-based learning environments. individuals are not reliable sources of information about themselves. However. Welsa (Popescu et al. (Lee 1994). it is also possible to deduce the styles from the analysis of these behaviours (Chen and Liu 2008). filling out a questionnaire about the preferred way of learning requires that the students are aware of their preferred way of learning. We must ask the learner the right questions. 2009)). Additionally. However. Thirdly. Regarding the format. dealing with how to detect the moment when a learning style has changed. They have all shown a strong relationshi p between learners‟ learning styles and their search and navigation behaviour in Web applications. However. automatically according to the assessment results. can influence their answers on the questionnaire. the social and psychological aspects. in general. the results of the questionnaires are no longer valid. such as the students‟ beliefs about how people should behave. Furthermore. structure and performance.404 Bousbia. is based on several assumptions (Graf 2007): Firstly. some studies have concluded that beyond explaining behaviour through learning styles. this approach of identifying learning styles raises several issues. et al.g. students would have to do it again in order to identify their new learning styles. we examine in the following some of this research and their findings. Our work follows this approach. Studies by (Chuang 1999). However. identified that the Masters students participating in their study about adaptation to learning styles had only little meta-knowledge on their learning preferences. for example. This is why. before explaining our proposal. several studies in psychology. and de Bra (2006). to assign him/her a style and adapt the system. face the problem that the answers may not correspond to the actual behaviour that questions are designed to check (Draper 1996.

These studies found that field dependent users promote the use of site maps to get an overview of the context and tend to follow the links provided by the Web page. Pask 1976) was studied by (Kraus.remain valid for these dimensions. spent more time to complete the test than those who used the system with a linear structure. (Marrison and Frick 1994) indicate that there is no difference between field dependent or independent users regarding the usefulness of audio resources in the training environment. and (Shih and Gamon 2002) (Lu. other studies have analyzed other dimensions of LS models. 2006).4.Knowledge Management & E-Learning: An International Journal. The learning styles of the model proposed by Gregorc (1979) have been studied in (Miller 2005) who found that the performance of learners is affected by their learning styles. as these field independent learners are more likely to have analytical LS (Jonassen and Grabowski 1993) (Reed et al. In terms of structure. field independent users use the index more to locate a particular point and tend to use search engines. the findings for these two dimensions . 2005) examined users‟ performance in linear and non -linear information structures. They found that field dependent learners who used the system with the nonlinear structure. (Lu. Yu and Liu 2003) regarding learning behaviour. Magoulas and Macredie 2004) and (Chen and Liu 2008). analytic users fit easily into all types of interfaces and demonstrated strong navigational skills. In (Kraus. (Federico 2000). in general. Regarding Kolb LS model (Kolb 1984). 2000). while those with a visual style prefer a relational structure of pages. As for accessibility. Reed and Fitzgerald 2001). some authors have echoed the findings for the field dependent and independent LS to other dimensions of LS models. with a global style. In this study (Kraus. passive and external LS.2. presenting a synoptic view of the information. and (Miller 2005) state that there is no significant difference between the four styles identified by Kolb when learning with hypermedia. However. For the other learning style models. In this study. The dimension verbal/imager proposed by Riding has been studied by (Graff 2005) with respect to navigation strategies. (Kraus. search function. 405 detailed resources. and usually URLs to reach the websites. 2005) and (Peterson and Deary. (Ford and Chen 2000) conducted a study to examine how learning styles influence users‟ browsing behaviour on the Web. (Dufresne and Turcotte 1997) (Reed and Oughton 1997) (Lee et al. (Calcaterra et al. the work of (Korthauer and Koubek 1994). (Hwang et al. (Palmquist and Kim 2000) and (Chen. The work of (Chen and Liu 2008) focused on the effects of the learning style on learning paths. Vol. Reed and Fitzgerald 2001). Besides. prefer adapted interface. However. Finally. the authors argue that field dependent users tend to have global (Pask 1976). 2007) concerning the number of annotations made. Magoulas and Macredie 2004) studied the influence of cognitive style on web search. 2001) also analyzed the visual/verbal dimension and noticed that users . Reed and Fitzgerald. Graff (2005) finds that users with a verbal style prefer a hierarchical structure. especially for novices.field dependent and independent . Among these studies. some studies found no difference between field dependent and independent LS on one or all of these aspects. Reed. active. No. and Fitzgerald 2001) the authors found that users. and internal. The global/analytic LS dimension proposed in several LS models (Felder and Silverman 1988. the studies of (Reed and al 2000). Therefore. For example in the work of (Chen. Yu and Liu 2003) and (DeTure 2004) found that field independent learners are more successful than those dependent upon learning with hypermedia resources. However. while field independent users tend to be analytic.

have been applied to them. and also web browsing. we are interested in the digital traces. registered in log files on the learner‟s side. they are nevertheless a significant factor. and not necessarily contains evaluations. In order to propose indicators applicable for Web-based educational systems. Finally. according to which users‟ behaviour in Web applications varies according to their learning styles. and any activity done in parallel.406 Bousbia. number of accesses of recommended learning objects versus not recommended ones (Popescu 2008)). it is worth noting that these studies are all based on the analysis of navigational behaviour of a sample of users or learners with Web applications. Chen. we aim at having indicators. This dimension. visual/verbal. On the other hand. We follow a different approach. (1985). influencing the reactions of learners in a hypermedia environment (Calcaterra et al. This recording defines a session. which provides online educational content to learners with educational activities. This indicator classifies the learner‟s navigation behaviour in four types (Bousbia et al. on the analysis of feedback that teachers want to have about their students through a survey we made with teachers (Bousbia and Labat 2007). Proposal In this research. To determine the indicators. Of course. even those made outside the learning system: the learner‟s interactions during his/her browsing path. We consider a Web-based learning environment. This approach allows tracing all the learner‟s activities. inspired from Web Usage Mining studies. which automatically deduces the learner‟s learning styles by analyzing his/her behaviour (Bousbia et al. 2008). these indicators are difficult to be interpreted by the teacher. or a Trace Based System (TBS). Thus. the indicators proposed in the literature to identify the learning styles based on trace analysis are generally quantitative and low-level indicators directly calculated from traces. the results of these studies can be used as criteria for the automatic identification of learners‟ learning styles on Web applications to replace LS questionnaires and solve their problems. we propose a „navigation type‟ indicator. Analysis techniques. with qualitative value describing the learning behaviour. Verbal users adapt easily to interfaces. Furthermore. require an adapted visual interface and have strong navigational skills. in general. as well as on the studies about the influence of learning styles on the learner‟s behaviour in a digital environment. generally these indicators are strongly linked to the EHS used. 2009): . we relied on the one hand. N. To summarize. 2005) (Liegle and Janicki 2006) (Dag and Geçer 2009). the learner decides the beginning and the end of the recording of its activities on his/her machine. However. we studied the state of the art on digital traces resulting from learning situations. mentioned above. that though learning styles are not the only source of difference in the users‟ behaviour on the Web. personal productions. before generalizing these findings. through this study. and usually related to duration or action frequency (eg. Thus. and Liu 2009). with statistical and data mining. was also analyzed by (Frias-Martinez. which are not necessarily prescribed by the content author: navigation within and between educational objects. we find. et al. 3. such as an elearning platform. In this context. mainly the navigation typology proposed by Canter et al.

2. derived from low and intermediate level indicators (Bousbia et al.). and (iii) high-level indicators. of each layer‟s attribute. the user seeks to acquire an overall “panoramic” view of the course. We assume here that the navigation type indicator is involved in the determination of many values of learning styles (see figure 1). This helps us to get a classification. environment preference (individual / group. Studying: corresponds to a partial or complete reading of the course pages. 2004). or more attributes (Bousbia et al. Cognitive ability layer: includes motivation and concentration capacity. often derived by a complex treatment of the traces (Dimatricopolou et al. 2008): Educational preferences layer: this layer includes attributes related to the preferred learning time. we classify learning styles into three layers. by making their definitions closer. information representations. we also classify the existing learning styles. . simulation. - - This indicator is a qualitative. The main difference with the overviewing type is the lack of focusing on the course. Deepening: is rather close to the preceding value. For this end. are chosen from the existing learning style models. and then deduce learning styles values. Then. Learning process layer: includes learning strategy. and seeking Web documents related to the course topics. Flitting: close to the Canter “wandering” value. 407 - Overviewing: this value is close to the Canter “scanning” value. The high-level indicators are therefore involved in determining the attributes of our model. 2009). and encoding methods (verbal / visual). - The values.4. with a span of time on each. we define links between these indicators in order to calculate automatically their values from traces to high-level indicators. Through this fast reading. with an interpretative value.Knowledge Management & E-Learning: An International Journal. comprehension. as shown in figure 1. It implies that the learner is covering a large proportion of pages constituting the course. we propose to define the indicator calculation methods by first classifying needed indicators at three levels: (i) low-level indicators. we think deductable from observable indicators. careful with details. Vol. Indeed. It is a journey without a strategy or a particular goal. or a model in which we need to define the dependence between indicators and learning styles. and progression approach. No. high-level indicator. To affirm this assumption. learning by project. we developed an experiment that we present in what follows. It describes a learner who remains a relatively long time on a course. each includes one. In fact. having no meaning alone and generally deducted directly from the raw data. according to the three definition elements. etc. (ii) intermediate or composite indicators.

4.408 Bousbia. However. We limited this experiment to such resources to focus on the learner's navigation behaviour from page to page in a Web learning environment. using an approach of matching pedagogical resources to the learning styles or a . the activities. we conducted an experiment at the ESI School.1. Methodology To identify differences in navigation behaviour among different learning style groups. Thus. et al. Research Instruments Research instruments work as a guide in order to make sure that the same information is obtained from different participants. considered in this case. Web based Course The context of this study was a hypermedia general course about “Computer Security”. Figure 1. N. the experimental design. and other activities. Its content is in HTML format and mostly contains text. and the methods of data analyses. 4. The research instruments used in this study included a Web based course and a learning style questionnaire to measure students‟ learning styles. the participants. This section describes the research instruments. the experiment can be repeated with other types of resources.1. From traces to learning styles 4. are consulting or reading activities that we generally found in all courses available on e-learning platforms.1.

Figure 2. we think the most commonly used in the majority of courses. SCORM requires a metadata file to include the course keywords. The first evaluates the user‟s level of field dependence. We used two learning style questionnaires widely used in literature: the Group Embedded Figures Test (GEFT) by Witkin et al. back. It also includes an introduction and a conclusion. (1971) and the Index of learning style (ILS) by Felder and Solomon (1996). 409 mismatching approach to check the learners‟ behaviour. The maximum total score is 18. 1 Sharable Content Object Reference Model. The runtime environment includes: (i) the course index.2. The subject's score is the number of simple shapes correctly identified in the complex forms. The course consultation is done on the eFAD platform (Bousbia 2005). it uses a tree structure. (ii) the platform navigation buttons in the top to visit the pages sequentially. needed to calculate some intermediate indicators. the subject is considered as field independent. Second.4. search. and (iii) the course content in the central frame. etc. Learning Style Questionnaire In this experiment we wanted to investigate several learning style attributes from those defined in our classification. print. http://www.2. If the score is high. The choice of SCORM was made for two reasons: first. The navigation environment also includes the browser interaction objects (the navigation buttons.1. No. integrated into two chapters: “threats” and “vulnerability”. It presents items containing complex geometrical forms in which the individual is required to find simple shapes on them. using the proposed indicators or others. The content is composed of 53 Web .Knowledge Management & E-Learning: An International Journal. next. A snapshot of the computer security course on the eFAD platform 4. and which our indicators are appropriate to. The course complies with the SCORM 1 standard. offering free access to the resources (the learner can hide this index using the button located above the text).) using the keyboard and/or the mouse.adlnet. (Figure 2). located in the left frame of the browser. Vol. copy /past.

Thus. with a personal account on the platform.3. Pithers.4. This prompts the student to view several pages of this part without having to read them thoroughly. all their scores were high with the GEFT test. Their participation was voluntary and they have not attended the course before. which is a scientific field. et al. in this study. they freely adopted one of the four behaviours that better fit their preferences.2. This corresponds to the “Overviewing” behaviour. we investigate here only the result of 27 participants. These preferences are expressed with values between +11 to -11 (with a step of +/-2) per dimension. Finally. The start and the end time of each session were noted down. The second presents a 44-item questionnaire for identifying the learning styles according to FSLSM (Felder and Silverman Learning Style Model) (Felder and Silverman 1996). The experiment was conducted in 5 sessions of 10 to 30 minutes. 2002) in (Tyndiuk 2005). Therefore. after activation of the collection tool. During the tests. 15 male and 12 female. the human observer is the teacher. We later found this conclusion in (Tinajero and Paramo. Navigation data are sequences of dated events (page access. For example. The observation starts with their connection to the e-learning platform. 1997. 4. a human observer (the experimenter) is present in the training room to ensure the normal progress of the experiment. In the last session. However. 4. For instance. may suddenly decide to look for precise information. N. a learner. However.410 Bousbia. they were asked to tak e the GEFT and the ILS tests. we only use the results of the ILS test. click. 27 log files were thus gathered. We asked the students to accomplish a chosen activity in every session to induce a given navigation behaviour according to the typology proposed in §2. The first four sessions involved only the first part of the course “threats”. since the data are still being processed. who underlined that this test is strongly correlated with academic performance: the science course students often score better than students in literature courses. These traces are then processed to compute behavioural indicators. In our case. etc. We divided each log file into 5 .). The motivation for this choice of short time browsing is the possible change of navigation strategy during the session. Every learner has a personal preference for each dimension. to characterize the students‟ learning styles. Procedure The students worked on machines equipped with the trace collection tool. the log files were stored in XML format for processing. Participants The experiment involved 116 graduate students at the National School of Computer Science (ESI-Algiers). Data Analysis At the end of the experiments. Clark et al. browsing a course. as all the participants are students in computer science. which are collected throughout the user‟s session. These students are aged between 18 and 24 years. we asked the students to browse according to their interests and needs through the pages of the second part of the course “Vulnerability”. 2000. 4. a question asks the student to extract the words in bold from a particular course part. they have not visited yet.

Table 1 summarizes the ILS questionnaire results for the 27 students. This test checks two hypothesises: H0: The learning styles and the navigation types are independent. The values 1-3 are interpreted as balanced between the two dimensions of the scale. the analysis is performed in two steps. They are associated to a mild preference level. Their results will not be discussed in this paper.2. given that these two variables have qualitative values. Otherwise. Learning Style Distribution First. we analyzed the distribution of preferences for each FSLSM dimension. First. The four sessions were used to evaluate the navigation type indicator. Next. we only focus on the last session in order to identify correlation between the navigation type indicator and the learning style attributes. If the calculated p-value is higher than the signification level (α = 0. However. Table 1. H0 is rejected and Ha is validated. No. 5. Results 5. the assumption H0 is validated. ILS Questionnaire Results ILS Results FSLSM Dimension ACT: Active REF: Reflective SEN: Sensing INT: Intuitive VIS: Visual VRB: Verbal SEQ: Sequential GLO: Global 9 – 11 (Strong preference: STG) 1 0 5 3 6 0 1 0 5-7 (Moderate preference: MOD) 7 3 5 2 9 2 5 4 1-3 (mild preference: MLD) 9 7 9 3 7 3 8 9 Total 17 10 19 8 22 5 14 13 .05). we evaluate the dependence between the two variables: learning style dimension and navigation type indicator. In order to conduct a comprehensive evaluation. Ha: The learning styles and the navigation types are dependent. The values 5-7 and 9-11 respectively present a moderate and strong preferences.4.1.Knowledge Management & E-Learning: An International Journal. we examine the observation distribution in terms of navigation behaviour found with the navigation type indicator over the preference levels of each learning style dimension of the FSLSM. 411 sessions considering the start and the end time of each activity.05). Vol. To this end. we use the chi-square test ( χ 2) with a signification level ( α =0.

et al. are found.2. The distribution of the participants over the sequential/global dimensions is quite equitable. deals with this point. To check if the differences. Navigation Type Indicator The navigation type indicator is a high level indicator. it is less equitable for the other dimensions. it is necessary to take into account this distribution during the analysis. Flitting 15% Deepening 7% Overviewing 56% Studying 22% Figure 3. However. The next step. The results of trace analysis of the fifth session of our experiment. which we are interested in here. Session Distribution. The calculation of its value is based on five intermediate indicators. mainly for the visual/verbal dimension where only 5 students. 5. According to the Navigation Type Indicator We notice that a great part of the sessions are classified as overviewing (15 observations). then studying (6 observations). .412 Bousbia. Thus. in this study. It can also result from their individual differences. (iv) the browsing pattern Fpc. (ii) the course duration rate Dc/Ds. Details about their calculation methods could be found in (Bousbia et al. in terms of learning styles. are presented in figure 3. This distribution can be due to the learners‟ will to discover the contents of this new part of the course before setting a clear objective. with a global learning style. 2009). used in this study. (iii) the course consultation type Tc. N. as shown is figure 1: (i) the average visit duration for a course page Dmc. and (v) the semantic proximity between the course and the content of the pages visited outside the course Prox. The next step is to analyse the students‟ log files to identify the navigation type related to each observation. according to their interests. flitting (4 observations) and finally deepening (2 observations). influence the navigation type used. we have to seek for significant relationships between the participants‟ learning style and the found navigation behaviours.

No. Figure 4 presents the students distribution according to their active/reflective preferences over the four navigation types found. discussing or explaining it to others. a studying navigation type. from left to right. 3 subjects adopted a navigation of overviewing type and the other 4. the other 2 a flitting one. using the navigation type indicator we have defined in 3.3. with moderate preference (ACT-MOD): 4 had an overviewing navigation type. when dealing with active learners. considering each preference level either separately (STG. MOD and . for the other 7 subjects. and 1 a flitting. In contrast. the correlation analysis between each FSLSM dimension and the navigation behaviour found for each learner. we can say that: the subject having a strong preference (ACT-STG) adopted the overviewing navigation type.1. When dealing with the reflective learners. 6 5 4 3 2 1 0 ACT-STG ACT-MOD ACT-MLD REF-MLD REF-MOD Overviewing Studying Deepening Flitting Figure 4. Active/Reflective Dimension This FSLSM dimension is used to describe the learner‟s preferred way to process information. among those having mild preference level (REF-MLD). Regarding the 9 students with mild preference for the active style (ACT-MLD). 5 adopted the overviewing navigation type. a subject made a deepening navigation type. 413 5. 2 the studying navigation type.2. Distribution of the Active/Reflective Learning Style Dimension in terms of ‘Navigation Type’ In this figure.Knowledge Management & E-Learning: An International Journal. Concerning the three subjects with moderate preference for the reflective style (REF-MOD). 2 adopted an overviewing navigation type. the other 3 are distributed this way: 1 made a deepening navigation type. reflective learners prefer to think about and reflect on the learning material (Felder et Silverman 1988). This shows that students with an active style tend more to make an overviewing navigation type. Active learners tend to better retain and understand information by working actively with the learning material. 5. Vol. we first introduce the definition of each dimension value. we present in the following subsections. then we discuss the results. and the other made a flitting one. Learning Styles and Navigation Behaviours To investigate the relationships between the FSLSM and the navigation type. About the last two students.4. applying. However.3.

Thus. this conclusion needs to be checked with a greater number of participants.414 Bousbia. et al.3. Indeed. we expect that reflective students take more time to read and think about the contents rather than actively interact. shows no existence of dependence between the active/reflective LS dimension and the navigation type values. This result corresponds to their active preference of information processing. the flitting navigation type. is significant. MLD) or by summoning the number of observations of subjects with active style. N. Intuitive learners prefer to discover new relationships and can be innovative in their approach to problem solving. However. It can be due to the fact that these subjects tend more to have a reflective style.287>0. as they quickly and actively explore the contents. sensing learners prefer learning facts and solving problems by well-established methods. However. the studying navigation type is more used by reflective students with mild preference that emphasizes our hypothesis. in the same way as the overviewing one. for this style. Distribution of the Observations in terms of ‘Navigation Type’ over the Sensing/Intuitive Learning Style Preference Level . In fact. Nevertheless. and patient and like new knowledge.05). Sensing/Intuitive Dimension According to Felder and Silverman (1988). They like to relate the learned material to the real world. They are generally careful. 7 6 5 Overviewing 4 3 2 1 0 SEN-STG SEN-MOD SEN-MLD INT-MLD INT-MOD INT-STG Studying Deepening Flitting Figure 5. by their tendency to make several actions. in second position the studying strategy. and those with a reflective style would rather prefer the studying navigation type. such as visiting several URLs. We also notice that subjects with moderate preference of the active style (ACT-MOD) use. 5.815. subjects with mild preference of the active style (ACT-MLD) use. as the majority of identified observations relate to the overviewing navigation type and the number of students with active style is more significant than the one with reflective style. we note that students with an active style tend more to adopt the overviewing navigation type.2. we notice that the number of observations with overviewing navigation behaviour. p-value = 0. The significant number of overviewing observations found during this experimentation may explain it. This can be justified. since the mild preference level is balanced between the two dimension axes. the result of the chi-2 independence test (χ2=7. Indeed. They tend to work faster and dislike repetition and tasks requiring great memorisation and routine calculations. in second position. practical.

We should carry on the analysis of the whole experimentation traces in order to clearly state this dependence. However. Thus.996. this dimension has been studied by (Graff 2005) with respect to navigation strategies. films. we note that sensing/intuitive LS and navigation type indicator are really dependent. whereas all those. with mild preference. as sensing learner like new knowledge. Distribution of the Observations in terms of ‘Navigation Type’ over the Visual/Verbal Learning Style Preference Level According to these definitions. here. 415 The distribution of the number of navigation types. may be to discover new relations between the course concepts and the results of the Web search. while verbal learners understand new information better through written and spoken words. though we do not manage to clearly identify this dependence. 2 out of the 3. However. a strong presence for the overviewing behaviour for students having a sensing style. adopted a deepening navigation type. The results of the chi-square test (χ2=24.05) indicate that the sensing/intuitive learning styles are dependent on the navigation type indicator. this navigation type is not found. This figure is read from left to right in the same way as in the preceding one.3. we have no hypothesis about the distribution of the observations on visual and verbal learners. with a moderate preference. with strong preference. for subjects with strong and moderate preference. we expected to find more deepening navigation behaviour.Knowledge Management & E-Learning: An International Journal. Vol. which appears not correlated with the definition of this learning style. However.4.3. as mentioned in section 2. demonstrations. We also note. 6 5 4 3 2 1 0 VIS-STG VIS-MOD VIS-MLD VRB-MLD VRB-MOD Overviewing Studying Deepening Flitting Figure 6. Those. adopted flitting and studying navigation behaviours. had an overviewing behaviour. Visual/Verbal Dimension Visual learners understand new information better by seeing it as pictures.3. 5. followed by flitting then studying ones. while those with a . In fact. is presented in figure 5. charts. etc. having intuitive style. for which students search on the Web. p-value= 0. He finds that users with a verbal style prefer a hierarchical structure.016<0. diagrams. For subjects. No.2. found for each observation over the participants‟ preference levels of the sensing/intuitive lea rning style dimension. no subject adopted a deepening navigation type.

However. unless we consider the relational structure from a semantic point of view. However. the course. .205>0. N. The finding for visual learners is interesting since it corroborates the considered results of (Graff 2005). We note that students with mild and moderate preference of visual learning style use more overviewing and studying navigation type.416 Bousbia. visual style prefer a relational structure of pages. Global learners tend to learn in large jumps by absorbing material in a random order without necessarily seeing any connections until the whole concept has been grasped. has a hierarchical structure. we note that global subjects with mild preference tend to be like sequential ones. However. who adopted all the navigation types. global learners are more likely to use the other navigation types. those with visual strong preference level also use deepening and flitting behaviours. Those with mild preference tend to be like the global ones. 6 5 4 3 2 1 0 SEQ-STG SEQ-MOD SEQ-MLD GLO-MLD GLO-MOD Overviewing Studying Deepening Flitting Figure 7. the experiment results are shown in figure 7.3. for the verbal style. the greater part of participants adopted the studying strategy. et al.026. the results of the chi-square test (χ2=21. and they may use the overviewing strategy as they tend to be active. the results found strengthen the previous hypothesis. Thus.4. To check this assumption. The results of our experiment are shown is figure 6. so they do not spend a long time on each page. So. However. 5. According to these definitions. Sequential/global dimension Sequential learners understand new information in linear steps where each step follows logically the previous one. we assumed that sequential learners tend to adopt the studying behaviour more than any other. we find that they use overviewing or flitting navigation type. However. used in this experiment. thus this navigation strategy corresponds to a studying or a deepening navigation type. the small number of subjects does not allow us to make any conclusion. For the verbal students.05) indicates that the visual/verbal learning styles are independent from the navigation type indicator. p-value=0. we can check this finding. Consequently. Distribution of the Observations in terms of ‘Navigation Type’ over the Sequential/Global Learning Style Preference Level We find that sequential learners with strong and moderate preferences adopt overviewing behaviour.

Stewart. pp. Bousbia. & Brailsford. 44(4). Antonietti. Brown..but to explain the learner‟s behaviour and take into account his/her learning style to adapt the content. found by our indicators over the LS preference levels. A.. A.. hypermedia navigation and learning. In INRP eds. In Proceedings of the WWW 2006 Conference.026. Labat. 327-335. p-value= 0. & J.. 6. Taiwan. Brown.. Algiers. the result of the chi-square test (χ2=21. Labat. in terms of navigation type. D.2. J. Vol. affirms this dependence for all FSLSM dimensions. (2006). C. Moore. I.. N. Rebai. We also need to make other experiments to check the existence of relationships with other learning style dimensions.. Bousbia. P. J-M. & Balla A..05) indicates that the sequential/global learning styles are independent from the navigation type indicator. pp..4. Labat (2007). Thus. Reappraising Cognitive Styles in Adaptive Web Applications. Fisher. Berlin Heidelberg. References 1 2 Ayersman. Calcaterra. to identify these dependences clearly. The Adaptive Web: Methods and Strategies of Web Personalization. A. T. pp. & Balla. Lausanne. the distribution of the collected observations. 371-390.643>0. 233-238. How to determine the Learners‟ Learning Styles in e-Learning Situation? The 16th International Conference on Computers in Education. & Underwood. Computers in Human Behavior. pp 385-389. 3--53. New York: Springer-Verlag.). K. A.. ICCE 2008. A. Indicators for Deducting the Learners' Learning Styles: Case of the Navigation Typology Indicator. Bousbia. Individual differences. Ecole nationale Supérieure d'Informatique (Esi ex INI). Brailsford.M. we can practically use this study findings. Contribution théorique et méthodologique à l'élaboration d'un environnement de FOAD (Formation ouverte et à distance). 77-90. A. . Perception de l‟activité de l‟apprenant dans un environnement de formation.J... a. & Millán. and instruction. Algeria. User models for adaptive hypermedia and adaptive educational systems. we need to carry on the analysis of all the experimentation traces. (2005). Cognitive style. T. I. (2005). N. T. and with other indicators. W. (2009). 4321. In Proceedings of the 9th IEEE International Conference on Advanced Learning Technologies ICALT 2009.why not other necessary indicators. as well. Bousbia. (1995). (2008).. (2005). 441-457... 07. & von Minden. & Ashman. However. E. N. Rebai. N.. 11 (3/4). In A. Taipei. Conclusions This study has demonstrated that relationships exist between learning styles and learners‟ navigation behaviour in Web-based environment. No. not only to automatically deduce the learner‟s learning style from the navigation type indicator . Brusilovsky (Ed.. 8(3). Vol. computers. (2007).. 417 Nevertheless. J ournal of Educational Technology and Society. E. 3 4 5 6 7 8 9 . Patterns in Authoring of Adaptive Educational Hypermedia: A Taxonomy of Learning Styles. Brusilovsky. E. Cristea. H.Knowledge Management & E-Learning: An International Journal. N.. EIAH 2007. Computers & Education. Although the chi-square dependency test shows the existence of such dependence only for the sensing/intuitive dimension over our sample. J. JM.

Learning styles and pedagogy in post-16 learning. R. (2008). Kao. Students‟ cognitive styles and the need for visual control in animation. J. & Lane W. Social and Behavioral Sciences. N. D. Stoner (Ed. 15(1).D. Howard. 862-871. In L. & Turcotte. Boulay. 14 Chen. XXVIII (1). S. K. In G.. 10 Carver.-R. (2009). (1990). C. . M. 42(1).). volume 1. Interactive Multimedia Electronic Journal of Computer-Enhanced Learning. ACM Transactions on Computer-Human Interaction (TOCHI). 4. Int J Digit Libr. . L. 15 Chen. & Ecclestone.). 273-285. Learning style in continuing medical education. Seat. Learning Technology Dissemination Initiative (pp. Measuring. C. D. (2000). R. A learning style classification mechanism for e-learning. 18(1). 21 Dag. and Mizoguchi. & Weber. The performance of engineering students on the group embedded figures test. 24 Dimitracopoulou et al. T. S.1. (2004). J. Teaching in a multimedia computer environment: a study of effects of learning style. (1997). E. (1983). and Learning Disabilities International. F. 1.A. 13 Chang. Fortin. W-Y. (1999). Théberge.-C.. 26 Dufresne.). Chu. Deliverable: D. G. In B. (Ed. (2000). C. 19(4). Moseley. Implementing Learning Technology. Le style d’apprentissage : une perspective historique. F. Kaleidoscope. 21-38. Amer. C-H.26. (2009). L. Le style d'apprentissage. 58-65). Comparison of eleven major learning styles models: Variables. JEIRP-ICALTS. & Geçer. R. (2003). Cognitive style and self-efficacy: Predicting student success in online distance education. and math achievement. & Liu. ACELF. 351-363. (1999). . Addressing different learning styles through course hypermedia. R. S. M. In Proceedings of the 8th Annual Conference of the European Learning Styles Information. : London: Learning and Skills Research Centre. 28. D.. An organization of learning style theory and constructs. 53(2). Distance Educ. 11 Cassidy... (1996). Artificial intelligence . A. (2004). Magoulas. 12 Chan-Lin. 93-107. or Evaluating Courseware: A Conceptual Introduction. A. 148p. An integrated approach for modeling learning patterns of students in Web-based instruction: A cognitive style perspective.& Macredie. 16 Chevrier. 23 Deture. L. Educ Comput Res. and research behind them. S. Observing. (2004). et al. (2004). Relations between online learning and learning styles. Computers & Education. Springer-Verlag.. Y..Writing. 17 Chuang. C-P. validity of instrumentation. Learning styles: an overview of theories. S. Journal of Reading. IEEE Transactions on Education. gender.. F. . (Ed. 25 Draper. models and measures. Cognitive style and its implications for navigation strategies. E. W. X. 19 Coffield. 18 Clark.. Hall. 20 Curry.. Y.Y. Canadian medical Association. 6(3). G. Ontario: Council on Medical education. . 203-222. & Le Blanc. Cognitive styles and users‟ responses to structured information representation. 22 DeBello. july 2004. pages T3A/1–T3A/4. & Chiu. S.. (1998). State of the Art on Interaction Analysis: Interaction Analysis Indicators.. appropriate populations. In Proceedings of the 30th Conference of the ASEE/IEEE Frontiers in Education. A. 33-38.418 Bousbia. Ottawa. Y.. . A systematic and critical review.

D.E. A.2.. A. L. C. Frias-Martinez. cognitive style and structure upon the performance of a hypertext task. Austria. What affect student cognitive style in the development of hypermedia learning system? . Individual differences in hypertext browsing strategies. S. G. Federico. Graff. SY. Thesis. W.. (2001). Computers in Human Behavior .Y. ... Amsterdam. (2000). Learning and Teaching Styles In Engineering Education.ncsu. and Mumford. New Jersey. (2003). Cheng. Jonassen. & Chen.html. & Koubek. M. M. International Journal of Human Computer Interaction. 45(1). International Journal of Information Management. Educ Multimedia Hypermedia. Kraus. 48-56. M. Lee.. J. British Journal of Educational Technology and Society. 125-140. 78(7).390.. 34(4). Kolb. and Instruction. 393-406.. C. 680-699. A. Computers and Human Behavior. C. Maidenhead: Peter Honey Publications. 24(2). B. PA. Korthauer. & Silverman. .. The effects of learning style and hypermedia prior experience on behavioral disorders knowledge and time on task: a case-based hypermedia environment. P. A. & Sharples. & Depickere..99. Soloman. 281-311. 287-293). Learning. Hwang. Comput&Educ. The Effect of Learning Styles on the Navigation Needs of Web-Based Learners. 6. 17(1). L. 16(4). Lawrence Erlbaum Associates. A study of multimedia annotation of Web-based materials. M. Handbook of Individual Differences. R. 36 (4). hypermedia navigation and learning: an empirical study. Vienna University of Technology. Y. Evaluation of a personalized digital library based on cognitive styles: Adaptivity vs. Y. J. (2005). 234-236. (1979). Unpublished EdD dissertation University Of Pittsburgh. 373 . S. A. Ford. X. (1994). Education. G. (1993). (1992). (1984).. Engr. L.. The impact of cognitive styles on perceptual distributed multimedia quality. The Manual of Learning Styles. (2007).M. An empirical evaluation of knowledge. W. (1996). (2009). (1988). & Grabowski. from http://www.F. A. Learning/Teaching Styles: Potent Forces behind Them. 29(1). Chen.engr. Retrieved 15 September. Individual differences. D. S. 359-379. Lee. Comput&Educ. S. 9(4). 674-681 Felder. 48(4). Rai. 885-898.. T. & Chen. New Jersey: Prentice Hall. Honey.. Reed. W. (2000). ILS: Index of Learning Styles. R. 22(5). H. R. Vol. Hillsdale. D. 419 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 in education knowledge and media learning system (pp. Experiential learning: experience as the source of learning and development.D.K. Gregorc. . Adaptativity in Learning Management Systems Foccussing on Learning Styles. P. (2007). 2009. . (1994). Computers in Human Behavior. & Liu. adaptability. 93 . R. N.. 1-19. B. Felder. Kobe (Japan): IOS Press. Behaviour and Information Technology. No. & Janicki. (2006). Liegle. (2005). Educational Leadership.Knowledge Management & E-Learning: An International Journal. Ghinea. Learning styles and student attitudes toward various aspects of network-based instruction.. Wang.4. Graf.. E.. The effects of auditory cues in interactive multimedia and cognitive style on reading skills of third graders. & Fitzgerald.

558566. A mixed approach to modelling learning styles in adaptive educational hypermedia. & Liu. & Deary. 26-30. & Trigano (2007)..). Cognitive learning style: a review of the field dependent-field independent approach. (2000). D. & Rodrí guez.J. 55 Pithers. J Am Soc Inf Sci. E. Trends and Issues in Instructional Technology . J.. Instructional Strategies and Learning Styles: Which Takes Precedence? In R. Cognitive style and on-line database search experience as predictors of Web search performance. (1994). (1997). (2002). 50 Palmquist. W.S. & Oughton. E. (1976). M. 446-450. 54(1). 54 Peterson. K-S. 46 Lu. et al. & Kim. Kornilakis H. Ervin. L. Personalizing the inter-action in a Web-based educational hypermedia system: the case of INSPIRE. (2006). 117132. 99-106. British Journal of Educational Psychology. Comput. The effect of agricultural students‟ learning styles on academic achievement and their perceptions of two methods of instruction. In Proceeding of the User-Modelling and User-Adapted Interaction conference. 16(6). T. . 51(6). M. 41(1). (2003). G. Computer experience. and hypermedia navigation. M.A. J.. E. 497-507. Learning style. 492-499. (1994). Computers in Human Behavior. 287-306. . D. 51 Papanikolaou K. (2002). W. (Eds. (2003). 59 Reed.. In Proceedings of the Ninth International Symposium on Symbolic and Numeric Algorithms for Scientific Computing. D. (2005). 58 Popescu. R. Learning Styles and Behavioral Differences in Web-Based Learning Settings. Ayersman. J.. 45 Liu. S. Romania.. learning style. 609-628. C. 210215. 60 Reed.M. Computers in Human Behavior. Advanced Technology for Learning. W. Prentice Hall. M.. OH.. 53 Pask. 30(1). 1(4). N. Personality and Individual Differences.. 40(6). (2008). & Reed. Journal of Vocational Education and Training. R. learning patterns. The effect of hypermedia assisted instruction on second-language learning through a semantic-network-based approach. & Frick. (2004).. Oughton. P. 35(1). and learning performance in a WebCT-based MIS course. Criova.. . Using learning styles to evaluate computer-based instruction. 38-52. I. 3-14. Examining wholistic-analytic style using preferences in early information processing. P. J. R.J..F. & Magoulas G.M.R.. 47 Marrison. ICALT 2009. Res.. D. (2009). C. Computer experience and interval-based hypermedia navigation. Yu. 49 Miller. 46. C. Columbus. (2000). pp. Educ. 56 Popescu. E. Rules for Learner Modeling and Adaptation Provisioning in an Educational Hypermedia System. 52 Paredes. JM. 48 Merrill. Badica.420 Bousbia. J Agric Educ. M. G.. Styles and Strategies of Learning. Res Comput Educ. 57 Popescu.J. Giessler. Dynamic adaptative hypermedia systems for e-learning. 159-175. In Proceedings of the 2009 Ninth IEEE International Conference on Advanced Learning Technologies. 21(2). 128-148. M. 12(2). Information and Management.

(2006). E. (1971).. 65 Tinajero. 421 61 Rich. S. Y-M. E. 68 Wang. C. E. London. Users are individuals: individualizing user models. (2007). A. Cristea. N. A.. Capuano. 7(1/2). British Journal of Educational Psychology. Using a style-based ant colony system for adaptive learning. 1-23. Journal of Universal Access in the Information Society.Knowledge Management & E-Learning: An International Journal. K. Oltman. 66 Triantafillou. T. 34(4). Cognitive styles and learning strategies. Field dependence-independence and academic achievement: a re-examination of their relationship. 69 Witkin. No.. Government. Healthcare.4. Référentiels Spatiaux des Tâches d’Interaction et Caractéristiques de l’Utilisateur influençant la Performance en Réalité Virtuelle. International Journal of Man-Machine Studies. The design and the formative evaluation of an adaptive educational system based on cognitive styles.. AACE. Computers & Education.. Ph. P. D. & Karp. F. 62 Riding. Palo Alto. 64 Stash. CA. A Manual For The Group Embedded Figures Test. 199-214. 87-103.-I.. 284-291. M. (2001). France. & Micarelli. Wang. A. Vol. & de Bra. Adaptive Course Generation through Learning Styles Representation....D thesis on Cognitive sciences. Raskin. 67(2). Pomportsis. Gaeta. N. . (2003). R. A. Expert Systems with Applications. (2008). & Demetriadis. A. K-T. Consulting Psychologists Press. Adaptation to Learning Styles in ELearning: Approach Evaluation. David Fulton Publishers. S. M. and Higher Education. 18(3).. 199–212. P. In Proceedings of the World Conference on ELearning in Corporate. H. 2449-2464. Bordeaux 2 University. 41(1). VA..2... F. & Huang. E. 67 Tyndiuk. & Rayner. 63 Sangineto. S. (1983). & Paramo. (2005). (1997). .

Sign up to vote on this title
UsefulNot useful