Paper Info
Title
Automatic creation of stock market lexicons for sentiment analysis using StockTwits data
Abstract
Sentiment analysis has been increasingly applied to the stock market domain. In particular, investor sentiment indicators can be used to model and predict stock market variables. In this context, the quality of the sentiment analysis is highly dependent of the opinion lexicon adopted. However, there is a lack of lexicons adjusted to microblogging stock market data. In this work, we propose an automatic procedure for the creation of such lexicon by exploring a large set of labeled messages from StockTwits, a popular financial microblogging service, and using four statistical measures: adaptations of the known TF-IDF, Information Gain, Class Percentage, and a newly proposed Weighted Class Probability. The obtained lexicons are competitive when compared with a set of six reference lexicons. Moreover, we verified that it is beneficial to use continuous sentiment scores instead of sentiment labels.
Year
DOI
Venue
2014
10.1145/2628194.2628235
IDEAS
Keywords
Field
DocType
database applications,algorithms,applications,experimentation,stock market,information retrieval,lexicon,content analysis and indexing,opinion mining,microblogging data,natural language processing,economics,sentiment analysis
Data mining,Social media,Sentiment analysis,Computer science,Information gain,Microblogging,Lexicon,Natural language processing,Artificial intelligence,Stock market
Conference
Citations 
PageRank 
References 
6
0.50
15
Authors
3
Name
Order
Citations
PageRank
Nuno Oliveira116015.80
P. Cortez210517.99
Nelson Areal3763.91