In this paper, we propose a measure of individual investor sentiment that is derived from the market for bank-issued warrants. Due to a unique warrant transaction data set from a large discount broker we are able to calculate a daily sentiment measure and test whether individual investor sentiment is related to daily stock returns by using vector autoregressive models and Granger causality test...

This paper describes our deep learning-based approach to sentiment analysis in Twitter as part of SemEval-2016 Task 4. We use a convolutional neural network to determine sentiment and participate in all subtasks, i.e. two-point, three-point, and five-point scale sentiment classification and two-point and five-point scale sentiment quantification. We achieve competitive results for two-point sca...

Previous studies have shown that investor sentiment indicators can predict stock market change. A domain-specific sentiment lexicon and sentiment-oriented word embedding model would help the sentiment analysis in financial domain and stock market. In this paper, we present a new approach to learning stock market lexicon from StockTwits, a popular financial social network for investors to share ...

Sentiment classification is a fundamental task in opinion mining. However, most existing systems require a sentiment lexicon to guide sentiment classification, which inevitably suffer from the problem of unknown words. In this paper, we present a morpheme-based fine-to-coarse strategy for Chinese sentence-level sentiment classification. To approach this, we first employ morphological productivi...

In this paper, we propose a measure of individual investor sentiment that is derived from the market for bank-issued warrants. Due to a unique warrant transaction data set from a large discount broker we are able to calculate a daily sentiment measure and test whether individual investor sentiment is related to daily stock returns by using vector autoregressive models and Granger causality test...

We examine the statistical power of fundamental and behavioral factors with regards to stock returns of the Dow Jones Industrials Index. With a novel sentiment dataset from over 3.6 million Reuters news articles, we nd signi cant correlations between Reuters sentiment and stock returns. We show with vector autoregression and error correction models that sentiment can explain and predict changes...

Chinese microblog is a popular Internet social medium where users express their sentiments and opinions.But sentiment analysis onChinese microblogs is difficult: The lack of labeling on the sentiment polarities restricts many supervised algorithms; out-of-vocabulary words and emoticons enlarge the sentiment expressions, which are beyond traditional sentiment lexicons. In this paper, emoticons i...

In this paper we examine the proposition that small investor sentiment, measured by the change in the discount/premium on closed-end funds, is an important factor in stock returns. We conduct an out-ofsample test of the investor sentiment hypothesis in a market environment that is more likely to be prone to investor sentiment than the U.S.. We fail to provide supporting evidence of the claim of...

Numerous sentiment analysis applications make usage of a sentiment lexicon. In this paper we present experiments on hybrid sentiment lexicon acquisition. The approach is corpus-based and thus suitable for languages lacking general dictionarybased resources. The approach is a hybrid two-step process that combines semisupervised graph-based algorithms and supervised models. We evaluate the perfor...