Negation scope detection in sentiment analysis: Decision support for news-driven trading

Sentence-Level Sentiment Analysis of Financial News Using Distributed Text Representations and Multi-Instance Learning

“…In research, ad hoc announcements are a frequent choice (e. g. [20,[27][28][29]) when it comes to evaluating and comparing methods for sentiment analysis. Additionally, this type of news corpus presents several advantages: ad hoc announcements must be authorized by company executives, the content is quality-checked by the Federal Financial Supervisory Authority, and several publications confirm their relevance to the stock market (e. g. [8]).…”

“…Over the last several years, researchers have created a great number of decision support systems that process financial news; in order to predict the resulting stock market reaction. The overwhelming majority of such systems described in previous works consider every financial news item as a single document with a given label, i. e. the stock market reaction (e. g. [7][8][9]). For the purpose of text categorization, researchers then transform documents into a representation suitable for the learning algorithm and the classification task.…”

“…In the existing literature, sentiment is predominately considered a measure of the qualitative information in financial news, referring to the degree of positivity or negativity of opinions shared by the authors with regard to individual stocks or the overall market [2,3]. In this context, the overwhelming majority of studies uses bag-of-words approaches to explain stock market returns, e. g. by the linguistic tone of ad hoc announcements (e. g. [8]), 8-K filings (e. g. [15,16]), newspaper articles (e. g. [17]) or company press releases (e. g. [18]). Comprehensive literature overviews regarding textual sentiment analysis of financial news can be found in [19], as well as [3].…”

“…Although many decision support systems have already been created for the prediction of the stock market direction, e. g. [8,9,20,21], their performance still remains unsatisfactory [19] and only marginally better than random guessing. One possible explanation is that determining the sentiment only at the document-level does not account for the relevances of different text segments.…”

Business analytics for strategic management: Identifying and assessing corporate challenges via topic modeling

“…On the one hand, various use cases require supervised learning with a priori labels. Examples include, for instance, automatic assignment of IT tickets to the correct service unit [19], forecasts of news-based stock price changes [20] or predicting users' affect [21]. Alternatives rely upon unsupervised methods, such as clustering or topic modeling, which are able to shed light on the patterns within business data.…”