Abstract—Business and financial news are important resources that investors referred to when monitoring the stock performance. News brings us the latest information about the stock market. Studies have shown that business and financial news have a strong correlation with future stock performance. Business and financial news can be used to extract sentiments and opinions that may assist in the stock price predictions. In this paper, we present a sentiment analyser for financial news articles using lexicon-based approach. We utilized two most important elements of news, the headline and the content as our test data. We use polarity lexicon to distinguish between positive and negative polarity of each term in the corpus. We further investigate on how news headline will affect the sentiment analysis by adjusting the weights of the news headline and news content’s sentiment value. Three sets of experiments were carried out using headline only, content only and headline and content as test data. In the experiment, we used non-stemming tokens and stemming tokens when considering individual word found in the news article. The preliminary results are presented and discussed in this paper.
Index Terms—Lexicon, news headline, news content, sentiment analysis.
Tan Li Im, Pang Wai San, Chin Kim On, and Rayner Alfred are with the Center of Excellence in Semantic Agents, Universiti Malaysia Sabah, Jalan UMS, 88400, Kota Kinabalu, Sabah, Malaysia (e-mail: email@example.com, firstname.lastname@example.org, email@example.com, firstname.lastname@example.org).
Patricia Anthony is with the Department of Applied Computing, Faculty of Environment, Society and Design, Lincoln University, Christchurch, New Zealand (e-mail: email@example.com ).
Cite: Tan Li Im, Phang Wai San, Chin Kim On, Rayner Alfred, and Patricia Anthony, "Impact of Financial News Headline and Content to Market Sentiment," International Journal of Machine Learning and Computing vol.4, no. 3, pp. 237-242, 2014.