Preprint Article Version 1 This version is not peer-reviewed

LexScore: A Semantic Approach to Scoring Domain Specific Sentiment Lexicons

Version 1 : Received: 13 June 2019 / Approved: 14 June 2019 / Online: 14 June 2019 (14:55:52 CEST)

How to cite: Kumar, S. LexScore: A Semantic Approach to Scoring Domain Specific Sentiment Lexicons. Preprints 2019, 2019060133 (doi: 10.20944/preprints201906.0133.v1). Kumar, S. LexScore: A Semantic Approach to Scoring Domain Specific Sentiment Lexicons. Preprints 2019, 2019060133 (doi: 10.20944/preprints201906.0133.v1).

Abstract

The sentiment of a word varies based on its context of usage: the words used around it and the part-of-speech it is used as. This paper proposes a technique to suggest the sentiment of a word by combining its part-of-speech and the semantic similarities of its co-occurrences with both context-specific and pre-trained embeddings to achieve powerful and fast results. A study was conducted across domains and sub-domains to measure variance of sentiment by switching domains and switching context within the same domain. Re-scoring a commonly used polarity lexicon showed that 10% of words changed scores while switching domains and 8% changed scores within domains while switching context. Part of Speech analysis on 65,353 commonly used sentiment lexicons showed that 81% of sentiment bearing (non-neutral) lexicons were of the tags NN (Common Noun), JJ (Adjective) or NNS (Proper Noun).        

Subject Areas

Natural Language Processing, Sentiment Analysis

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our diversity statement.

Leave a public comment
Send a private comment to the author(s)
Views 0
Downloads 0
Comments 0
Metrics 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.