A Mini Project

on

“Language Detector”
Submitted in partial fulfillment of the requirements
of the degree of

Bachelor of Engineering (Sem-VIII)

By

1. Prasad shinde (Roll.No. 62)

2. Abhishek Singh (Roll.No. 64)
3. Devesh Upadhayay (Roll.No. 70)
4. Tushar Wankhede (Roll.No. 75)

Supervisor:

Dr. D. R. Ingle

Department of Computer Engineering

Bharati Vidyapeeth College of Engineering, Navi Mumbai
C.B.D Belapur, Navi Mumbai-400614
(Affiliated to University of Mumbai)

Academic Year 2021-2022

 Department of Computer Engineering

Bharati Vidyapeeth College of Engineering, Navi Mumbai

CERTIFICATE
This is to certify that

1. Tushar Wankhede (Roll.No. 75)

2. Devesh Upadhayay (Roll.No. 70)
3. Abhishek Singh (Roll.No. 64)
4. Prasad shinde (Roll.No. 62)
has satisfactorily completed the requirements of the mini project entitled

“Language Detector”
as prescribed by the University of Mumbai, for the award of the degree of Bachelor
of Engineering in Computer Engineering

Dr. D.R.Ingle Dr. Sandhya Jadhav

Head Of Department Principal

 ACKNOWLEDGEMENT
I take this opportunity to express my deepest gratitude and appreciation to all those who
have helped me directly or indirectly towards the successful completion of this dissertation report.

It is a great pleasure and moment of immense satisfaction for me to express my profound

gratitude to my dissertation Project Guide, Prof. D. R. Ingle whose constant encouragement enabled
me to work enthusiastically. His perpetual motivation, patience and excellent expertise in discussion
during progress of the dissertation work have benefited me to an extent, which is beyond
expression. I am highly indebted to him for his invaluable guidance and ever-ready support in the
successful completion of this dissertation in time. Working under his guidance has been a fruitful and
unforgettable experience. Despite of his busy schedule, he was always available to give me advice,
support and guidance during the entire period of my project. The completion of this project would
not have been possible without his encouragement, patient guidance and constant support. I
express my deepest sense of gratitude & thanks to Prof. D. R. Ingle for her continuous support, and
guidance throughout this work.

I am thankful to Prof. D. R. Ingle, Head of Computer Engineering Department, for their guidance,
encouragement and support during my project. I would like to mention here that he was
instrumental in making available all the needed resources throughout my project. I am highly
indebted to him for his kind support.

I am also thankful to Dr. Sandhya Jadhav, Principal, for his encouragement and for providing an
outstanding academic environment, also for providing the adequate facilities.I acknowledge all the
staff members of the department of Computer Engineering for their valuable guidance with their
valuable guidance with their interest and valuable suggestions brightened me.

No words are sufficient to express my gratitude to my beloved Parents for their unwavering
encouragement in every work. I also thank all friends for being a constant source of my support. 

Name : Tushar Wankhede (Roll.No. 75)

Devesh Upadhayay (Roll.No. 70)

Abhishek Singh (Roll.No. 64)
Prasad shinde (Roll.No. 62)
 Abstract

In today’s digital world where there is an endless variety of content to be

consumed like books, videos, articles, movies, etc., finding the content of one’s
liking has become an irksome task. On the other hand, digital content providers
want to engage as many users on their service as possible for the maximum
time.

This is where recommender system comes into picture where the content
providers recommend users the content according to the users’ liking.
Nowadays, the recommendation system has made finding the things easy that
we need.

Movie Mender aim at helping movie enthusiasts by suggesting what

movie to watch without having to go through the long process of choosing from
a large set of movies which go up to thousands and millions that is time
consuming and confusing. Our aim is to reduce the human effort by suggesting
movies.
 Introduction
What is a recommender system?

A recommender system is a simple algorithm whose aim is to provide the

most relevant information to a user by discovering patterns in a dataset. The
algorithm rates the items and shows the user the items that they would rate
highly. An example of recommendation in action is when you visit Amazon and
you notice that some items are being recommended to you or when Netflix
recommends certain movies to you. They are also used by Music streaming
applications such as Spotify and Deezer to recommend music that you might
like.

A recommendation system is a model which is used to filter information and

predict the output based on the preferences of the user. These models have
become extremely popular that they are being used in movies, books, television,
restaurants, food etc. These systems help in improving the future suggestion of
the company. A large number of companies are benefiting from the
recommendation system in improving customer satisfaction and experience. In
this way they are collecting massive chunks of revenue which is why most of
them are turning to a recommendation system.

Below is a very simple illustration of how recommender systems work in

the context of an e-commerce site.

Two users buy the same items A and B from an e-commerce store. When
this happens the similarity index of these two users is computed. Depending on
the score the system can recommend item C to the other user because it detects
that those two users are similar in terms of the items they purchase.
1. Problem Statement
People spend a lot of time on watching the movies or web series. But they
are still confused which movie to be viewed. So, to solve this problem our
project predicts and recommend a movie.

2. Problem Definition
Due to wide-spread adoption & innovations of technologies, we are able
to stream movies/tv shows straight onto our gadgets. This led to rise of
OTT platforms. In order pump in the customer churn, they need a robust
recommendation system to keep them hooked in.

A recommendation system is a type of information filtering system which

attempts to predict the preferences of a user, and make suggests based on
these preferences. The problems arise in form of providing related content
out of relevant and irrelevant collection of items to users of online service
providers

3. Existing Models
Over the years, many recommendation systems have been developed
using either collaborative, content based or hybrid filtering methods. These
systems have been implemented using various big data and machine
learning algorithms.

The authors propose a collaborative recommendation system which is

designed to work on the Hadoop platform, using the Map Reduce
framework. The authors have used the set-similarity join method to build
this system, employing both user-based and item-based collaborative
filtering techniques.

They proposed a movie recommendation system using collaborative

filtering that focuses on the ratings given by the users to provide
recommendations. The proposed system is built using K-means algorithm to
sort the movies according to the ratings

In our project, we implemented a movie recommendation system to

recommend movies.
 Literature Survey

MOVREC is a movie recommendation system presented by D.K. Yadav

et al. based on collaborative filtering approach. Collaborative filtering makes
use of information provided by user. That information is analyzed and a movie
is recommended to the users which are arranged with the movie with highest
rating first.

Luis M Capos et al has analyzed two traditional recommender systems

i.e., content based filtering and collaborative filtering. As both of them have
their own drawbacks he proposed a new system which is a combination of
Bayesian network and collaborative filtering.

A content filter-based system has been presented by Harpreet Kaur et al.

The context of the movies is also considered while recommending. The user -
user relationship as well as user - item relationship plays a role in the
recommendation.

Recently social network analysis has been used in the various

applications. However, studies on recommender systems using social network
analysis are deficient. Henceforth, we expect that new recommendation
approaches using social network analysis will be developed in the recommender
systems. So, it will be an interesting and further research area to evaluate the
recommendation system researches using social method analysis.

This result provides trend of recommender system researches by

examining the published literature, and provides practitioners and researchers
with insight and future direction on recommender systems.
 Proposed Methodology
Recommendation systems can be broadly classified into 3 types —

• Collaborative Filtering
• Content-Based Filtering
• Hybrid Recommendation Systems

Collaborative Filtering

This filtering method is usually based on collecting and analyzing

information on user’s behaviors, their activities or preferences, and predicting
what they will like based on the similarity with other users. A key advantage of
the collaborative filtering approach is that it does not rely on machine
analyzable content and thus it is capable of accurately recommending complex
items such as movies without requiring an “understanding” of the item itself.

Content-based filtering

These filtering methods are based on the description of an item and a

profile of the user’s preferred choices. In a content-based recommendation
system, keywords are used to describe the items, besides, a user profile is built
to state the type of item this user likes. In other words, the algorithms try to
recommend products that are similar to the ones that a user has liked in the past.
Hybrid Recommendation Systems

Recent research has demonstrated that a hybrid approach, combining

collaborative filtering and content-based filtering could be more effective in
some cases. Hybrid approaches can be implemented in several ways, by making
content-based and collaborative-based predictions separately and then
combining them, by adding content-based capabilities to a collaborative-based
approach (and vice versa), or by unifying the approaches into one model.py.

The Cosine Similarity

The cosine similarity between two vectors (or two documents on the
Vector Space) is a measure that calculates the cosine of the angle between them.
This metric is a measurement of orientation and not magnitude, it can be seen as
a comparison between documents on a normalized space because we’re not
taking into the consideration only the magnitude of each word count (tf-idf) of
each document, but the angle between the documents. What we have to do to
build the cosine similarity equation is to solve the equation of the dot product
for the :
Mean Absolute Error
Mean Absolute Error (MAE): MAE measures the average magnitude of
the errors in a set of predictions, without considering their direction. It’s the
average over the test sample of the absolute differences between prediction and
actual observation where all individual differences have equal weight.

If the absolute value is not taken (the signs of the errors are not removed),
the average error becomes the Mean Bias Error (MBE) and is usually intended
to measure average model bias. MBE can convey useful information, but should
be interpreted cautiously because positive and negative errors will cancel out.

Root mean squared error (RMSE):

RMSE is a quadratic scoring rule that also measures the average
magnitude of the error. It’s the square root of the average of squared differences
between prediction and actual observation.
Experimental Results
 Conclusion

A Collaborative System based filtering approach is taken to implement

the system. A key advantage of the collaborative filtering approach is that it
does not rely on machine analyzable content and thus it is capable of accurately
recommending complex items such as movies without requiring an
“understanding” of the item itself.

Techniques like Clustering, Similarity and Classification are used to get

better recommendations thus reducing MAE and increasing precision and
accuracy. In future we can work on hybrid recommender using clustering and
similarity for better performance. Our approach can be further extended to other
domains to recommend songs, video, venue, news, books, tourism and e-
commerce sites, etc.

Future Scope

This system can be improved by building a Memory-Based Collaborative

Filtering based system. In this case, we’d divide the data into a training set and
a test set. We’d then use techniques such as cosine similarity to compute the
similarity between the movies. An alternative is to build a Model-based
Collaborative Filtering system. This is based on matrix factorization. Matrix
factorization is good at dealing with scalability and sparsity than the former.
You can then evaluate your model using techniques such as Root Mean Squared
Error (RMSE).
 References

[1] Video Lecture on Mideo Recommender Systems in Machine Learning Course on

Coursera by Andrew Ng
[2] Matrix Factorization Techniques For Recommender Systems, Yehuda Koren,
Robert Bell, Chris Volinsky
[3] Algorithms and Methods in Recommender Systems, Daniar Asanov
[4] Peng, Xiao, Shao Liangshan, and Li Xiuran. "Improved Collaborative Filtering
Algorithm in the Research and Application of Personalized Movie
Recommendations",
[5] A Nearest Neighbor Approach using Clustering on the Netflix Prize Data
[6] Movie Recommendation and Rating Prediction using K-Nearest Neighbors by
Heeral Dedhia on www.analyticsvidhya.com