Matheus Tangeni Shikomba
ABSTRACT
Twitter has grown in popularity during the past decades. It is now used by millions of users who share information about their daily life and their opinions on certain topics in the media. In order to automatically process and analyse this data, applications can rely on analysis methods such as sentiment analysis. This study aimed to find correlations between the sentiments of tweets and newspaper headlines in the Namibian context. It focused on using Twitter because of its limitation in the length of the text content posted on this platform.
The study revealed the correlation between the sentiments of Tweets posted from Namibia and that of national headlines appearing in local newspapers.
The study is carried out using Design and Creation Method as it involves capturing data from the Twitter social media platform using an application that has been developed to the needs of the study, headlines from Namibian newspapers namely The Namibian, New Era, Namibian SUN, Informante and Confidente have been captured manually. This application will also track the sentiment score of Namibian tweets in real time. Additionally, the study also made use of the Qualitative and Quantitative Research Methods to analysed and draw conclusions from the collected qualitative data.
The study analysed the sentiment score of the tweets and the newspaper headlines collected, the sentiment scores were graphically plotted to find the sentiment correlation between tweets and newspaper headlines, as well as notable trends. Real-time sentiment analysis of tweets was also carried out to determine the sentiment score of Namibian tweets over a certain period particularly days and months.
This study showed us that there is a direct sentiment correlation between tweets and news headlines, whenever the sentiment score of news headlines drops that of tweets drops as well, and this is more evident when looking at the monthly correlation graph in the results section. This implies that news headlines are one of the drivers of social media content in Namibia.
- A. Goel, J. Gautam, and S. Kumar, "Real time sentiment analysis of tweets using Naive Bayes," 2016, pp. 257--261.Google Scholar
- T. Schreiner, "Information, Opinion, or Rumor? The Role of Twitter During the Post-Electoral Crisis in Côte d'Ivoire," Social Media + Society, vol. 4, no. 1, p. 205630511876573, Jan. 2018.Google ScholarCross Ref
- H. T. Gemilang, A. Erwin, and K. I. Eng, "Indonesian president candidates 2014 sentiment analysis by using Twitter data," 2014, pp. 101--104.Google Scholar
- H. Thakkar and D. Patel, "Approaches for Sentiment Analysis on Twitter: A State-of-Art study," p. 8, May 2018.Google Scholar
- natural language processing definition - Google Search." [Online]. Available: https://www.google.com.na/search?q=natural+language+processing+definition&rlz=1C1CHBD_enNA800NA800&oq=natural+language+processing+definition&aqs=chrome.0.0l6.16102j1j4&sourceid=chrome&ie=UTF-8. [Accessed: 14-Nov-2018].Google Scholar
- sentiment analysis | Definition of sentiment analysis in English by Oxford Dictionaries." [Online]. Available: https://en.oxforddictionaries.com/definition/sentiment_analysis. [Accessed: 12-Nov-2018].Google Scholar
- H. Wang, D. Can, A. Kazemzadeh, F. Bar, and S. Narayanan, "A System for Real-time Twitter Sentiment Analysis of 2012 U.S. Presidential Election Cycle," in Proceedings of the ACL 2012 System Demonstrations, Jeju Island, Korea, 2012, pp. 115--120.Google Scholar
- M. Bhumika, "Analysis of Various Sentiment Classification Techniques," International Journal of Computer Applications, vol. 140, no. 3, pp. 22--27. Apr. 2016.Google ScholarCross Ref
- A. Baj-Rogowska, "Sentiment Analysis of Facebook Posts: The Uber Case," Dec. 2017.Google Scholar
- K. Wilfred Kiprono, "Comparative Twitter Sentiment Analysis Based on Linear and Probabilistic Models," International Journal on Data Science and Technology, vol. 2, no. 4, p. 41, 2016.Google ScholarCross Ref
- A. Goel, J. Gautam, and S. Kumar, "Real time sentiment analysis of tweets using Naive Bayes," 2016, pp. 257--261.Google Scholar
- D. Quercia, J. Ellis, L. Capra, and J. Crowcroft, "Tracking 'gross community happiness' from tweets," 2012, p. 965.Google ScholarDigital Library
- Natural Language Toolkit --- NLTK 3.3 documentation." [Online]. Available: https://www.nltk.org/. [Accessed: 21-May-2018].Google Scholar
- B. Oates, Researching Information Systems and Computing. London: SAGE Publications, 2006.Google ScholarDigital Library
- Twitter API Tutorial. [Online]. Available: http://socialmediaclass.org/twittertutorial.html. [Accessed: 11-Nov-2018].Google Scholar
- H. Kim, S. M. Jang, S.-H. Kim, and A. Wan, "Evaluating Sampling Methods for Content Analysis of Twitter Data," Social Media + Society, vol. 4, no. 2, p. 205630511877283, Apr. 2018.Google Scholar
- TextBlob Sentiment: Calculating Polarity and Subjectivity." [Online]. Available: https://planspace.org/20150607-textblob_sentiment/. [Accessed: 22-Nov-2018].Google Scholar
- 41 Incredible Instagram Statistics you Need to Know," Brandwatch. [Online]. Available: https://www.brandwatch.com/blog/instagram-stats/. [Accessed: 21-Nov-2018].Google Scholar
- Top 20 Facebook Statistics - Updated November 2018," Zephoria Inc., 20-Nov-2018.Google Scholar
- TextBlob: Simplified Text Processing --- TextBlob 0.16.0 documentation'. https://textblob.readthedocs.io/en/dev/ (accessed May 21, 2021).Google Scholar
- A. Kulkarni and A. Shivananda, 'Exploring and Processing Text Data', in Natural Language Processing Recipes: Unlocking Text Data with Machine Learning and Deep Learning using Python, A. Kulkarni and A. Shivananda, Eds. Berkeley, CA: Apress, 2019, pp. 37--65. doi: 10.1007/978-1-4842-4267-4_2.Google ScholarCross Ref
- K. H. Manguri, R. N. Ramadhan, and P. R. M. Amin, 'Twitter Sentiment Analysis on Worldwide COVID-19 Outbreaks', Kurdistan Journal of Applied Research, pp. 54--65. May 2020, doi: 10.24017/covid.8.Google ScholarCross Ref
Index Terms
- Correlation of Sentiment Analysis between Tweets and Newspaper Headlines Using NLP
Recommendations
Followee recommendation based on topic extraction and sentiment analysis from tweets
iiWAS '15: Proceedings of the 17th International Conference on Information Integration and Web-based Applications & ServicesTwitter has become a popular social media service, accumulating and distributing vast amounts of information for its numerous users. One feature of Twitter is that it enables a user to follow other users, who can obtain the information her/his followees ...
A sentiment analysis of audiences on twitter: who is the positive or negative audience of popular twitterers?
ICHIT'11: Proceedings of the 5th international conference on Convergence and hybrid information technologyMicroblogging is a new informal communication medium of blogging that differs from a traditional blog in which content is much shorter. Microbloggers post about topics that describe their current status. Twitter is a popular microblogging service and ...
Searching for relevant tweets based on topic-related user activities
Twitter is one of the largest social media. Although it can be used to get information on a topic of interest, it is not easy for us to find tweets relevant to the topic due to a massive amount of tweets and the small size of each tweet. Some relevant ...
Comments