IITP at SemEval-2017 Task 5: An Ensemble of Deep Learning and Feature Based Models for Financial Sentiment Analysis

Proceedings of the 11th International Workshop on Semantic Evaluations (SemEval-2017), pages 899–903, Vancouver, Canada, August 3 - 4, 2017. c⃝2017 Association for Computational Linguistics IITP at SemEval-2017 Task 5: An Ensemble of Deep Learning and Feature Based Models for Financial Sentiment Analysis Deepanway Ghosal, Shobhit Bhatnagar, Md Shad Akhtar, Asif Ekbal, Pushpak Bhattacharyya Indian Institute of Technology Patna, India {deepanway.me14,shobhit.ee14,shad.pcs15,asif,pb}@iitp.ac.in Abstract In this paper we propose an ensemble based model which combines state of the art deep learning sentiment analysis algo- rithms like Convolution Neural Network (CNN) and Long Short Term Memory (LSTM) along with feature based mod- els to identify optimistic or pessimistic sentiments associated with companies and stocks in financial texts. We build our sys- tem to participate in a competition orga- nized by Semantic Evaluation 2017 Inter- national Workshop. We combined predic- tions from various models using an artifi- cial neural network to determine the opin- ion towards an entity in (a) Microblog Messages and (b) News Headlines data. Our models achieved a cosine similarity score of 0.751 and 0.697 for the above two tracks giving us the rank of 2nd and 7th best team respectively. 1 Introduction Sentiment analysis of financial text is an impor- tant area of research. It has been shown that sen- timents and opinions can affect market dynam- ics (Goonatilake and Herath, 2007). Social me- dia has created a new world of venting customer voice. People tend to express their personal sen- timent about the stock market through tweets. On the other hand, news presents the macroeconomic factors, company-specific or political information. Positive news tend to bring optimism and lift the market where as negative news effect the market in opposite direction (Van de Kauter et al., 2015). Sentiment analysis gives organizations the ability to observe the various social media sites in real time and then act accordingly. Twitter is consid- ered to be an ocean of sentiment data. A study indicates that sentiment analysis of public mood derived from Twitter feeds can be used to eventually forecast movements of individ- ual stock prices (Smailovi´c et al., 2014). All these evidences show us that financial sentiment analy- sis has a lot of untapped power and extensive re- search in the field can help us gain great insight about the financial market. The fundamental prob- lem with classifying financial tweets is the pres- ence of noise. The natural use of short, infor- mal languages, emoticons, hashtag and sarcasm in tweets makes the sentiment analysis problem es- pecially challenging. News headlines usually use limited number of words to summarize the article. Moreover, as- pects like language patterns, writing style, irony usage differs notably among different news cate- gories and articles. Use of articles, verb form of ‘to be’, conjunction are very rare in practice. In this paper we describe our proposed system as part of the ‘SemEval-2017 Task 5 on Fine- Grained Sentiment Analysis for Financial Mi- croblogs and News’ (Cortis et al., 2017). We pro- pose a multilayer perceptron (MLP) based ensem- ble …

Content truncated to 500 words