Abstract

This paper presents a novel method for contextualizing and enriching large semantic knowledge bases for opinion mining with a focus on Web intelligence platforms and other high-throughput big data applications. The method is not only applicable to traditional sentiment lexicons, but also to more comprehensive, multi-dimensional affective resources such as SenticNet. It comprises the following steps: (i) identify ambiguous sentiment terms, (ii) provide context information extracted from a domain-specific training corpus, and (iii) ground this contextual information to structured background knowledge sources such as ConceptNet and WordNet. A quantitative evaluation shows a significant improvement when using an enriched version of SenticNet for polarity classification. Crowdsourced gold standard data in conjunction with a qualitative evaluation sheds light on the strengths and weaknesses of the concept grounding, and on the quality of the enrichment process.

Highlights

  • Communication experts and decision makers aim to understand how stakeholders perceive their announcements and actions, and how news coverage and social media channels affect these perceptions

  • Humans excel at interpreting contradictory and context-dependent evidence. Leveraging this ability, the evaluation of the presented approach has been conducted as part of the uComp project, which merges collective human intelligence and automated knowledge extraction methods in a symbiotic fashion

  • A quantitative evaluation of context-aware sentiment analysis is followed by a hybrid assessment of the concept grounding and concept enrichment processes, combining a qualitative approach with quantitative measures obtained through the Crowdflower marketplace

Read more

Summary

Introduction

Communication experts and decision makers aim to understand how stakeholders perceive their announcements and actions, and how news coverage and social media channels affect these perceptions. To address these questions, this article describes the integration and automated extension of semantic knowledge repositories. Building upon a novel approach to contextualized sentiment analysis [19], we introduce methods that can ground and enrich identified concepts. This integration of semantic knowledge repositories is an important stepping stone towards making sense of big data. Communication experts who are responsible for marketing and public outreach campaigns, for example, want to know if their

Methods
Results
Discussion
Conclusion
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call