Impact of Financial News Headline and Content to Market Sentiment
Saved in:
| Title: | Impact of Financial News Headline and Content to Market Sentiment |
|---|---|
| Authors: | Tan, LI, Phang, WS, Chin, KO, Alfred, R, Anthony, Patricia |
| Source: | International Journal of Machine Learning and Computing. 4:237-242 |
| Publisher Information: | EJournal Publishing, 2014. |
| Publication Year: | 2014 |
| Subject Terms: | 05 social sciences, 1. No poverty, 02 engineering and technology, 0506 political science, ANZSRC::4605 Data management and data science, news content, sentiment analysis, 8. Economic growth, 0202 electrical engineering, electronic engineering, information engineering, news headline, ANZSRC::4603 Computer vision and multimedia computation, Lexicon |
| Description: | 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. |
| Document Type: | Article |
| ISSN: | 2010-3700 |
| DOI: | 10.7763/ijmlc.2014.v4.418 |
| Access URL: | http://www.ijmlc.org/papers/418-LC056.pdf https://researcharchive.lincoln.ac.nz/bitstream/10182/7021/1/Impact%20of%20Financial%20News%20Headline%20and%20Content%20to%20Market.pdf https://eprints.ums.edu.my/id/eprint/12226 http://www.ijmlc.org/index.php?m=content&c=index&a=show&catid=45&id=457 http://www.ijmlc.org/papers/418-LC056.pdf https://researcharchive.lincoln.ac.nz/handle/10182/7021 |
| Accession Number: | edsair.doi.dedup.....de3896ae3ae498322a0bae93b4098f8c |
| Database: | OpenAIRE |
Nájsť tento článok vo Web of Science | 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. |
|---|---|
| ISSN: | 20103700 |
| DOI: | 10.7763/ijmlc.2014.v4.418 |