Sentiment Analysis of X (Formerly Twitter) Using Machine Learning

Year : 2024 | Volume : 11 | Issue : 02 | Page : 28 37
    By

    Archana Bhardwaj,

  • Avinash Dubey,

  • Devesh Sharma,

  • Anshul Sharma,

  • Deepak Dayma,

  1. Assistant Professor, Department of Computer Science and Engineering, Poornima College of Engineering, Jaipur, Rajasthan, India
  2. Student, Department of Computer Science and Engineering, Poornima College of Engineering, Jaipur, Rajasthan, India
  3. Student, Department of Computer Science and Engineering, Poornima College of Engineering, Jaipur, Rajasthan, India
  4. Student, Department of Computer Science and Engineering, Poornima College of Engineering, Jaipur, Rajasthan, India
  5. Student, Department of Computer Science and Engineering, Poornima College of Engineering, Jaipur, Rajasthan, India

Abstract

Sentiment analysis is a methodology to determine the nature and behavior of each and every user for the content posted on the social media platform in the form of post and feed. Consumers of the online platform are encouraged to post reviews of the product that they purchase. Little attempt is created by Amazon to confine or limit the content of these reviews. The number of reviews for various merchandise changes, but the reviews determine accessible and abundant data for rather smooth reasoning for a range of requests. This paper inquires to administer and offer the current work in the field of the study of computers and belief reasoning to data repaired from Amazon. Preliminary data analysis through fitting and handling files for enumerations, natural language processing (NLP), and data performance. Logistic regression is used to categorize a given review as helpful or negative with 98.74% accuracy. A corpus contains 50,000 product reviews from 20 products, which serve as the dataset of study. Top sale and inspected books on the site are the basic focus of the experiments, factors that contribute to misclassification are identified and distinguished from those most beneficial in classification of different news output. The visages, in the way that bag-of-words and term frequency–inverse document frequency, are distinguished to each one in their influence in correctly tagging reviews. Mistakes in categorization and approximate troubles concerning the election of countenance are resolved and discussed. The purpose of this paper is to investigate a narrow unspecified main problem: beneficial and negative reviews about product. Sentimental analysis attempts to decide what facets of the text indicate their framework (helpful, negative, objective, tangible, etc.) and to build orders to appropriate these looks. The problem of classifying content as positive or negative is not all problem essentially, but it determines a plain enough action for progression. This project was founded to showcase an excellent logical product that improves people’s lives by providing practical solutions. Startups and electronics companies that create a type of output that solve the authentic-experience question, these companies make money to support living through these product.

Keywords: Application programming interface (API), natural language processing (NLP), machine learning (ML), sentiment analysis, algorithm

[This article belongs to Journal of Software Engineering Tools & Technology Trends ]

How to cite this article:
Archana Bhardwaj, Avinash Dubey, Devesh Sharma, Anshul Sharma, Deepak Dayma. Sentiment Analysis of X (Formerly Twitter) Using Machine Learning. Journal of Software Engineering Tools & Technology Trends. 2024; 11(02):28-37.
How to cite this URL:
Archana Bhardwaj, Avinash Dubey, Devesh Sharma, Anshul Sharma, Deepak Dayma. Sentiment Analysis of X (Formerly Twitter) Using Machine Learning. Journal of Software Engineering Tools & Technology Trends. 2024; 11(02):28-37. Available from: https://journals.stmjournals.com/josettt/article=2024/view=155779


References

  1. Adal H, Promy N, Srabanti S, Rahman M. Android based advanced attendance vigilance system using wireless network with fusion of bio-metric fingerprint authentication. In: 2018 20th International Conference on Advanced Communication Technology (ICACT), Chuncheon, South Korea, February 11–14, 2018. pp. 217–222.
  2. Sawant V, Shah K. A survey of distributed association rule mining algorithms. J Emerg Trends Comput Inform Sci. 2014; 5 (5): 391–398.
  3. Kamsu-Foguem B, Rigal F, Mauget F. Mining association rules for the quality improvement of the production process. Expert Syst Appl. 2013; 40 (4): 1034–1045.
  4. Berry MJ, Linoff GS. Data Mining Techniques for Marketing, Sales, and Customer Relationship Management. New York, NY, USA: John Wiley & Sons; 2004.
  5. Elsalamony HA. Bank direct marketing analysis of data mining techniques. Int J Comput Appl. 2014;85(7):12-22. doi: 10.5120/14852–3218.
  6. Wu SY, Fan HH. Activity-based proactive data management in mobile environments. IEEE Trans Mobile Comput. 2009; 9 (3): 390–404.
  7. Smita PS, Sharma P. Use of data mining in various fields: a survey paper. IOSR J Computer Eng. 2014; 16 (3): 18–21.
  8. Sharma A, Sharma R, Sharma VK, Shrivastava V. Application of data mining–a survey paper. Int J Computer Sci Inform Technol. 2014; 5 (2): 2023–2025.
  9. Asif M, Ahmed J. Analysis of effectiveness of Apriori and frequent pattern tree algorithm in software engineering data mining. In: 2015 6th International Conference on Intelligent Systems, Modelling and Simulation, Kuala Lumpur, Malaysia, February 9–12, 2015. pp. 28–33.
  10. Nengsih W. A comparative study on market basket analysis and Apriori association technique. In: 2015 3rd International Conference on Information and Communication Technology (ICoICT), Nusa Dua, Bali, Indonesia, May 27–29, 2015. pp. 461–464.
  11. Haque TU, Saber NN, Shah FM. Sentiment analysis on large scale Amazon product reviews. In: 2018 IEEE International Conference on Innovative Research and Development (ICIRD), Bangkok, Thailand, May 11–12, 2018. pp. 1–6.
  12. Bhatt A, Patel A, Chheda H, Gawande K. Amazon review classification and sentiment analysis. Int J Computer Sci Inform Technol. 2015; 6 (6): 5107–5110.
  13. Rain C. Sentiment Analysis in Twitter Reviews Using Probabilistic Machine Learning. Swarthmore, PA, USA: Swarthmore College; 2013. pp. 1–7.
  14. Nandal N, Tanwar R, Pruthi J. Machine learning based aspect level sentiment analysis for Amazon products. Spatial Inform Res. 2020; 28 (5): 601–607.
  15. Elmurngi EI, Gherbi A. Unfair reviews detection on Twitter reviews using sentiment analysis with supervised learning techniques. J Comput Sci. 2018; 14 (5): 714–726.
  16. Almjawel A, Bayoumi S, Alshehri D, Alzahrani S, Alotaibi M. Sentiment analysis and visualization of Amazon Books’ reviews. In: 2019 2nd International Conference on Computer Applications & Information Security (ICCAIS), Riyadh, Saudi Arabia, May 1–3, 2019. pp. 1–6.
Regular Issue Subscription Review Article
Volume 11
Issue 02
Received 06/05/2024
Accepted 15/06/2024
Published 09/07/2024
341

Login


My IP

PlumX Metrics