NLG301 at SemEval-2017 Task 5: Fine-Grained Sentiment Analysis on Financial Microblogs and News

Short length, multi-targets, target relationship, monetary expressions, and outside reference are characteristics of financial tweets. This paper proposes methods to extract target spans from a tweet and its referencing web page. Total 15 publicly available sentiment dictionaries and one sentiment dictionary constructed from training set, containing sentiment scores in binary or real numbers, are used to compute the sentiment scores of text spans. Moreover, the correlation coefficients of the price return between any two stocks are learned with the price data from Bloomberg. They are used to capture the relationships between the interesting target and other stocks mentioned in a tweet. The best result of our method in both subtask are 56.68% and 55.43%, evaluated by evaluation method 2.