Conference paper Open Access

Towards Bootstrapping a Polarity Shifter Lexicon using Linguistic Features

Schulder, Marc; Wiegand, Michael; Ruppenhofer, Josef; Roth, Benjamin

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.

This work was partially supported by the German Research Foundation (DFG) under grants RU 1873/2-1 and WI4204/2-1.
18
13
views
downloads
All versions This version
Views 1818
Downloads 1313
Data volume 2.4 MB2.4 MB
Unique views 88
Unique downloads 1010

Share

Cite as