ICTACT Journal on Image and Video Processing

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Evaluating Popular Smartphone Brands Based On Twitter Sentiment Using Textblob


Affiliations
1 Department of Computer Science, Periyar University, India
2 Department of Computer Science, Salem Sowdeswari College, India
     

   Subscribe/Renew Journal


In today’s world, social media plays a critical part in the advancement of industries, organizations, and businesses. It has been seen as a fundamental aspect that should be known to both businesses and individuals. In one way or another, everyone is associated with social media. People have been able to interact and exchange knowledge because of the mix of technology and social relationships. In the last 10 years or so, social media has become a governing medium for knowledge exchange. Sentiment Analysis (SA) allows users to express their emotions, perspectives, and opinions to the rest of the universe. Twitter is a big and quickly expanding microblogging social networking website wherein users may express themselves concisely and easily. A large number of consumer reviews for various items are emerging on Twitter. Mobile phones are a popular sector where a large number of consumer evaluations can be found. This makes it tough for a prospective consumer to read them and decide whether or not to purchase the goods. Only the precise aspects of the phones about which users have comments, as well as whether those opinions are good or negative are of importance to us. This paper proposes a solution to this problem by analyzing consumer sentiment from Twitter data to determine brand reputation based on customer happiness. In this work, Python programming is employed to perform tests on various tweets utilizing the Twitter API and for tweet pre-processing, the Natural Language Tool Kit (NLTK) package is used. The tweets dataset is then analyzed using Textblob and the intriguing results in negative, positive, and neutral emotions are displayed using various visualizations.

Keywords

Mobile Phone, Net Brand Reputation (NBR), Twitter, NLTK, Textblob
Subscription Login to verify subscription
User
Notifications
Font Size

  • J. Praveen Gujjar and H.R. Prasanna Kumar, “Sentiment Analysis: Textblob for Decision Making”, International Journal of Scientific Research and Engineering Trends, Vol.7, No. 2, pp. 1-13, 2021.

  • Statista, Available at https://www.statista.com/statistics/282087/numberofmonthly- active-twitter-users/, Accessed at 2017.

  • Varsha Sahayak, Vijaya Shete and Apashabi Pathan, “Sentiment Analysis on Twitter Data”, International Journal of Innovative Research in Advanced Engineering, Vol. 2, No. 1, pp. 1-13, 2015.

  • Neha Tyagi, Sharik Ahmad, Aamir Khan and M. Mazhar Afzal, “Sentiment Analysis Evaluating the Brand Popularity of Mobile Phone by using Revised Data Dictionary”, International Journal of Engineering Science Invention, Vol. 7, No. 3, pp. 53-61, 2018.

  • K.L. Santhosh Kumar, “Opinion Mining and Sentiment Analysis on Online Customer Review”, Proceedings of International Conference on Computational Intelligence and Computing Research, pp. 1-5, 2016.

  • Momina Shaheen, “Sentiment Analysis on Mobile Phone Reviews using Supervised Learning Techniques”, International Journal of Modern Education and Computer Science, Vol. 7, No. 1, pp. 32-43, 2019.

  • Hema Krishnan, M. Sudheep Elayidom and T. Santhanakrishnan, “Sentiment Analysis of Tweets for Inferring Popularity of Mobile Phones”, International Journal of Computer Applications, Vol. 157, No. 2, pp. 113, 2017.

  • Sharik Ahmad, Neha Tyagi, Umesh Chandra and Mohd. Maaz, “Sentiment Analysis Evaluating Net Brand Reputation of Mobile Phones using Polarity”, Proceedings of IEEE International Conference on Parallel, Distributed and Grid Computing, pp-20-22, 2018.

  • Y. Wang, K. Kim, B. Lee and H. Young, “Word Clustering based on POS Feature for Efficient Twitter Sentiment Analysis”, Human-centric Computing and Information Sciences, Vol. 8, No. 17, pp. 1-14, 2018.

  • Praveen Gujjar and H.R. Prasanna Kumar, “Sentimental Analysis for Running Text in Email Conversation”, International Journal of Computer Science and Engineering, Vol. 9, No. 4, pp. 67-69, 2020.

  • Ditiman Hazarika, Gopal Konwar, Shuvam Deb and Dibya Jyoti Bora, “Sentiment Analysis on Twitter by using TextBlob for Natural Language Processing”, Proceedings of the International Conference on Research in Management and Tech Innovation, Vol. 27, No. 1, pp. 63-67, 2020.

  • K. Gurumoorthy and P. Suresh, “Comparative Study of Recent Algorithms used in Natural Language Processing”, Parishodh Journal, Vol. 9, No. 2, pp. 66-73, 2020.

  • K. Gurumoorthy and P. Suresh, “Identification of Explicit Smartphone Feature using Apriori Algorithm”, International Journal of Advanced Science and Technology, Vol. 29, No. 3, pp. 8560869, 2020.

  • K. Gurumoorthy and P. Suresh, “A Novel Approach of an Online Review using Opinion Mining Motions by Comparing various Mobile Gadgets”, International Journal of Innovative Technology and Exploring Engineering, Vol. 8, No. 9, pp. 1-11, 2019.

  • K. Gurumoorthy and P. Suresh, “Supervised Machine Learning algorithm using Sentiment Analysis based on Customer Feedback for Smartphone Product”, International Journal of Emerging Trends in Engineering Research, Vol. 8, No. 8, pp. 1-9, 2020.

  • Shadi I. Abudalfa and Moataz A. Ahmed, “Semi-Supervised Target-Dependent Sentiment Classification for MicroBlogs”, Journal of Computer Science and Technology, Vol. 19, No. 1, pp. 1-13, 2019.

  • P. Suresh and K. Gurumoorthy, “Mining of Customer Review Feedback using Sentiment Analysis for SmartPhone Product”, Turkish Journal of Computer and Mathematics Education, Vol. 12 No. 10, pp. 5515-5523, 2021.

  • S. Muthukumaran and P. Suresh, “Text Analysis for Product Reviews for Sentiment Analysis using NLP Methods”, International Journal of Engineering Trends and Technology, Vol. 47, No. 8, pp. 474-480, 2017.

  • H. Saif, Y. He, M. Fernandez and H. Alani, “Contextual Semantics for Sentiment Analysis of Twitter”, Information Processing and Management, Vol. 52, No. 1, pp. 5-19, 2016.


Abstract Views: 247

PDF Views: 0




  • Evaluating Popular Smartphone Brands Based On Twitter Sentiment Using Textblob

Abstract Views: 247  |  PDF Views: 0

Authors

K. Gurumoorthy
Department of Computer Science, Periyar University, India
P. Suresh
Department of Computer Science, Salem Sowdeswari College, India

Abstract


In today’s world, social media plays a critical part in the advancement of industries, organizations, and businesses. It has been seen as a fundamental aspect that should be known to both businesses and individuals. In one way or another, everyone is associated with social media. People have been able to interact and exchange knowledge because of the mix of technology and social relationships. In the last 10 years or so, social media has become a governing medium for knowledge exchange. Sentiment Analysis (SA) allows users to express their emotions, perspectives, and opinions to the rest of the universe. Twitter is a big and quickly expanding microblogging social networking website wherein users may express themselves concisely and easily. A large number of consumer reviews for various items are emerging on Twitter. Mobile phones are a popular sector where a large number of consumer evaluations can be found. This makes it tough for a prospective consumer to read them and decide whether or not to purchase the goods. Only the precise aspects of the phones about which users have comments, as well as whether those opinions are good or negative are of importance to us. This paper proposes a solution to this problem by analyzing consumer sentiment from Twitter data to determine brand reputation based on customer happiness. In this work, Python programming is employed to perform tests on various tweets utilizing the Twitter API and for tweet pre-processing, the Natural Language Tool Kit (NLTK) package is used. The tweets dataset is then analyzed using Textblob and the intriguing results in negative, positive, and neutral emotions are displayed using various visualizations.

Keywords


Mobile Phone, Net Brand Reputation (NBR), Twitter, NLTK, Textblob

References