IITPB at SemEval-2017 Task 5: Sentiment Prediction in Financial Text

Proceedings of the 11th International Workshop on Semantic Evaluations (SemEval-2017), pages 894–898, Vancouver, Canada, August 3 - 4, 2017. c⃝2017 Association for Computational Linguistics IITPB at SemEval-2017 Task 5: Sentiment Prediction in Financial Text Abhishek Kumara, Abhishek Sethib, Md Shad Akhtara, Asif Ekbala Chris Biemannc, Pushpak Bhattacharyyaa,b aIndian Institute of Technology Patna, India bIndian Institute of Technology Bombay, India cUniversit¨at Hamburg, Germany {abhishek.ee14,shad.pcs15,asif,pb}@iitp.ac.in {abhisethi,pb}@cse.iitb.ac.in biemann@informatik.uni-hamburg.de Abstract This paper reports team IITPB’s partic- ipation in the SemEval 2017 Task 5 on ‘Fine-grained sentiment analysis on finan- cial microblogs and news’. We developed 2 systems for the two tracks. One sys- tem is based on an ensemble of Support Vector Classifier and Logistic Regression. This system relis on Distributional The- saurus (DT), word embeddings and lexi- con features to predict a continuous senti- ment value between -1 and +1. The other system is based on Support Vector Regres- sion using word embeddings, lexicon fea- tures, and PMI scores as features. Our sys- tems are ranked 5th in track 1 and 8th in track 2. 1 Introduction We are living in a world where stock market di- rectly affects the economic system of a country. Therefore, a reliable and prompt delivery of in- formation plays an important role in the financial market. Up until the last decade printed/television news were the major source of stock market- related information. However, with the introduc- tion of micro-blogging websites (e.g. Twitter etc.) the trend has been shifted. The rise of Twitter and StockTwits has given the people and organizations an opportunity to vent out their feelings and views. This information can be used by an individual or an organization to make an informed prediction re- lated to any company or stock (Si et al., 2013). This opens a new avenue for sentiment analysis in the financial domain of microblogs and news. News headlines are a short piece of text de- scribing the nature of an article. Due to space constraints, headlines normally follow a compact writing style, known as headlinese, which limits the usage of articles, the verb form of to be, con- junctions etc. Similarly, social media platforms text is prone to noise. There is a very high possibility of the data lacking a proper structure, grammar and appropriate punctuations. These inconsistencies make it challenging to solve any NLP prob- lems including sentiment analysis (Khanarian and Alwarez-Melis, 2012). Moreover, each tweet can have reference to multiple company names (or stock symbols) and the expressed sentiment can be different towards different companies. Hence, there is a need to perform fine-grained sentiment analysis wherein, generally, a context is used to decide the relevant portion of a tweet for a particu- lar company. Another inherent challenge with the microblog and news data is the use of short lan- guages, hashtag, emoticons and embedded URL. Special attention should be given to these as they can provide some important hidden information (Mohammad et al., 2013). Example - #bullish- Market and #increasingProfit can reflect positive sentiment. These are some of the …

Content truncated to 500 words