Negation Scope Detection for Sentiment Analysis: A Reinforcement Learning Framework for Replicating Human Interpretations

38 Pages Posted: 17 Dec 2020

See all articles by Nicolas Pröllochs

Nicolas Pröllochs

University of Freiburg - Information Systems Research; Justus Liebig University Giessen

Stefan Feuerriegel

LMU Munich

Bernhard Lutz

University of Freiburg

Dirk Neumann

University of Freiburg

Date Written: August 22, 2020

Abstract

Textual materials represent a rich source of information for improving the decision-making of people, businesses and organizations. However, for natural language processing (NLP), it is difficult to correctly infer the meaning of narrative content in the presence of negations. The reason is that negations can be formulated both explicitly (e.g., by negation words such as "not") or implicitly (e.g., by expressions that invert meanings such as "forbid") and that their use is further domain-specific. Hence, NLP requires a dynamic learning framework for detecting negations and, to this end, we develop a reinforcement learning framework for this task. Formally, our approach takes document-level labels (e.g., sentiment scores) as input and then learns a negation policy based on the document-level labels. In this sense, our approach replicates human perceptions as provided by the document-level labels and achieves a superior prediction performance. Furthermore, it benefits from weak supervision; meaning that the need for granular and thus expensive word-level annotations, as in prior literature, is replaced by document-level annotations. In addition, we propose an approach to interpretability: by evaluating the state-action table, we yield a novel form of statistical inference that allows us to test which linguistic cues act as negations.

Keywords: unstructured data, information processing, decision-making, natural language processing, reinforcement learning, negations

Suggested Citation

Pröllochs, Nicolas and Pröllochs, Nicolas and Feuerriegel, Stefan and Lutz, Bernhard and Neumann, Dirk, Negation Scope Detection for Sentiment Analysis: A Reinforcement Learning Framework for Replicating Human Interpretations (August 22, 2020). Available at SSRN: https://ssrn.com/abstract=3679167 or http://dx.doi.org/10.2139/ssrn.3679167

Nicolas Pröllochs (Contact Author)

University of Freiburg - Information Systems Research ( email )

Kollegiengebäude II
Platz der Alten Synagoge
Freiburg, 79098
Germany

Justus Liebig University Giessen ( email )

Licher Strasse 74
Giessen, 35394
Germany

Stefan Feuerriegel

LMU Munich ( email )

Geschwister-Scholl-Platz 1
Munich, 80539
Germany

HOME PAGE: http://www.ai.bwl.lmu.de

Bernhard Lutz

University of Freiburg ( email )

Fahnenbergplatz
Freiburg, D-79085
Germany

Dirk Neumann

University of Freiburg ( email )

Albert-Ludwigs-Universität Freiburg, Wirtscha.inf.
Kollegiengebäude II, Platz der Alten Synagoge
Freiburg im Breisgau, 79098
Germany

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
59
Abstract Views
334
Rank
648,767
PlumX Metrics