Investigate Peoples Social Media Behaviours Using Tweets from Twitter

Abstract

Introduction

I. INTRODUCTION

There is huge amount of data available on Twitter. This data provides lots of valuable information related to particular topic. Company has thousands of clients but it is difficult for them to reach each and every client to know their personal advice, feedback and opinions. But there are tweets available on Twitter related to particular topic. We can utilize this information for improvement of organization, company or any famous personality. So, we can analyse their performance and according to that they can achieve success.

A. Title and Author Details

B. Section Headings

No more than 3 levels of headings should be used.  All headings must be in 10pt font.  Every word in a heading must be capitalized except for short minor words as listed in Section III-B.

1. Proposed Work:  There is a huge amount of data available on Twitter. Gleaning information from that storage is a big challenge. The system takes Tweets available on twitter as a input, then preprocess the Tweets and perform sentiment analysis. This results in the classification of Tweets into three classes such as positive, negative and neutral.
2. Project Modules There are three main modules : 1. Data Collection. 2. Data Preprocessing. 3. Sentiment Analysis. Level-3 Heading:  A level-3 heading must be indented,  in Italic and numbered with an Arabic numeral followed by a right parenthesis. The level-3 heading must end with a colon.  The body of the level-3 section immediately follows the level-3 heading in the same paragraph.  For example, this paragraph begins with a level-3 heading.

C. Figures and Tables

D. Table Captions

PROPOSED SYSTEM ARCHITECTURE System architecture is the conceptual model that defines the structure behaviour and more use of system. System architecture consist of four stages.

1. Data Collection Stage: In this system, tweets are collected from twitter. These tweets are related to trending topics like organizations, famous personalities, music, sports, politics etc. These collected tweets contain the information such as time, text, date, country, language. These tweets are in json format.
2.  Pre-Processing of Data: The data that we get is in json format. This format makes it easy for humans to read the data and for machines to parse it. That data is stored in the data frame. \
3. Data Modelling: Stored data from the data frame is converted into tokens.
4. Sentiment Analysis:  Intensity of that token is calculated. According to intensity, polarity gets assign to respective token. Based on the polarity score, tweets are classified into positive, negative and neutral.

II. ACKNOWLEDGMENT

We are glad to forward this project report as an image of sincere efforts. The successful project reflects our work, effort of our guide in giving us good information. We would like to express our heartiest thanks to our project guide Mr. Pratape.P.P for her undying support which makes us possible to make this project knowledgeable. She not only provided us the literature and guidance to study but also the platform which is required for us to prepare best for this project. We are also equally indebted to our project coordinator Mr. Pratape.P.P who has been a constant source of inspiration and guiding star in achieving our goal. We thank Mr.Pratape.P.P Head of Department Information Technology and Hon. Principal for supporting and providing all facilities to complete the work. We are thankful to and fortunate enough to get constant encouragement, support and guidance from entire teaching staff of Department of Information Technology which helped us in successfully completing our project work.

Conclusion

Social media is a huge source of information where massive amount of data can be generated everyday. Retrieval and pre-processing of that data is a complex task. For utilization of that data, we collect information about individual and entities, measure their interaction and discover pattern to understand behaviour. By performing sentiment analysis, proposed system will be able to determine opinions and views of people regarding celebrities and organization in the form of sentiments. Python language is helpful for collecting the sentiments in the form of positive, negative and neutral score. For better understanding of the user, the result is shown in the graphical format. Proposed system is helpful for individual/organization to improve and increasing their marketing and business strategies.

References

[1] Ardra,Blessy Merin Varughese, Merline Susan Joseph, Preethi Elsa Thomas,Sherly K K,“Analyzing the Behavior of Youth to Sociality Using Social Media Mining, International Conference on Intelligent Computing and Control Systems ICICCS 2017,pp.1231-1235. [2] Reza Zafarani, Mohammad Ali Abbasi and Huan Liu, “Social Media Mining-An Introduction”, 2014, A Book [3] B. Sriram, D. Fuhry, E. Demir, H. Ferhatosmanoglu, and M. Demirbas, “Short text class cation in twitter to improve information ltering”, In Proceeding of the 33 rd internationalACM SIGIR conference on Research and development in information retrieval, 2010, pp. 841842. [4] J. Sankaranarayanan, H. Samet, B. E. Teitler, M. D. Lieberman, and J.Sperling, “Twitterstand: news in tweets”, in Proceedings of the 17th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, 2009 , pp. 4251. [5] Manisha Rani, JyotiArora, “Twitter Data Predicting Geolocation Using Data Mining Techniques”, International Journal of Innovative Research in Computer and Communication Engineering, June2016, vol. 4, no.6, pp. 10446-10453 [6] Shruti Wakade, Chandra Shekar, Kathy J. Liszka and Chien-Chung Chan. Text Mining for Sentiment Analysis of Twitter Data. [7] Luciano Barbosa and Junlan Feng,“ Robust sentiment detection on twitter from biased and noisy data, Proceedings of the 23rd International Conference on Compu tational Linguistics: Posters , 2010, pp. 36-44. [8] Sameesksha Shrivastava, Dr. Pramod S. Nair, “Mood Prediction on Tweets Using Class cation Algorithm”, International Journal of Science and Research, 2015, vol. 4, no. 11, pp. 295-299.

Copyright

Copyright © 2022 Vitthal Bangar, Rohit Bhosale, Prasanna Kulkarni, Shubham Zingade. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.