10.5281/zenodo.3365609
https://zenodo.org/records/3365609
oai:zenodo.org:3365609
Schulder, Marc
Marc
Schulder
0000-0002-4183-8489
Spoken Language Systems, Saarland University
Wiegand, Michael
Michael
Wiegand
Spoken Language Systems, Saarland University
Ruppenhofer, Josef
Josef
Ruppenhofer
Institute for German Language, Mannheim
Roth, Benjamin
Benjamin
Roth
Center for Information and Language Processing, LMU Munich
Towards Bootstrapping a Polarity Shifter Lexicon using Linguistic Features
Zenodo
2017
Sentiment Analysis
Sentiment Polarity
Negation
Lexical Semantics
Lexicon
NLP Resources
2017-11-27
eng
https://www.aclweb.org/anthology/I17-1063
10.5281/zenodo.3364812
10.5281/zenodo.3370051
10.5281/zenodo.3365608
https://zenodo.org/communities/natural-language-processing
Creative Commons Attribution 4.0 International
We present a major step towards the creation of the first high-coverage lexicon of polarity shifters. In this work, we bootstrap a lexicon of verbs by exploiting various linguistic features. Polarity shifters, such as “abandon”, are similar to negations (e.g. “not”) in that they move the polarity of a phrase towards its inverse, as in “abandon all hope”. While there exist lists of negation words, creating comprehensive lists of polarity shifters is far more challenging due to their sheer number. On a sample of manually annotated verbs we examine a variety of linguistic features for this task. Then we build a supervised classifier to increase coverage. We show that this approach drastically reduces the annotation effort while ensuring a high-precision lexicon. We also show that our acquired knowledge of verbal polarity shifters improves phrase-level sentiment analysis.
Supplementary Data
Verbal Shifter Lexicon: doi:10.5281/zenodo.3364812
Sentiment Verb Phrases: doi:10.5281/zenodo.3364812
Word Embedding: doi:10.5281/zenodo.3370051
This work was partially supported by the German Research Foundation (DFG) under grants RU 1873/2-1 and WI4204/2-1.