Understanding Negations in Information Processing: Learning from Replicating Human Behavior

by   Nicolas Pröllochs, et al.

Information systems experience an ever-growing volume of unstructured data, particularly in the form of textual materials. This represents a rich source of information from which one can create value for people, organizations and businesses. For instance, recommender systems can benefit from automatically understanding preferences based on user reviews or social media. However, it is difficult for computer programs to correctly infer meaning from narrative content. One major challenge is negations that invert the interpretation of words and sentences. As a remedy, this paper proposes a novel learning strategy to detect negations: we apply reinforcement learning to find a policy that replicates the human perception of negations based on an exogenous response, such as a user rating for reviews. Our method yields several benefits, as it eliminates the former need for expensive and subjective manual labeling in an intermediate stage. Moreover, the inferred policy can be used to derive statistical inferences and implications regarding how humans process and act on negations.


page 1

page 2

page 3

page 4


Explicit User Manipulation in Reinforcement Learning Based Recommender Systems

Recommender systems are highly prevalent in the modern world due to thei...

Language That Matters: Statistical Inferences for Polarity Identification in Natural Language

Information forms the basis for all human behavior, including the ubiqui...

A Quantitative Study of the Impact of Social Media Reviews on Brand Perception

This thesis can be categorized under the Influencer Marketing industry w...

Evolution of the Online Rating Platform Data Structures and its Implications for Recommender Systems

Online rating platform represents the new trend of online cultural and c...

Content Recommendation through Semantic Annotation of User Reviews and Linked Data - An Extended Technical Report

Nowadays, most recommender systems exploit user-provided ratings to infe...

Using consumer feedback from location-based services in PoI recommender systems for people with autism

When suggesting Points of Interest (PoIs) to people with autism spectrum...

Please sign up or login with your details

Forgot password? Click here to reset