TY  - CHAP
U1  - Konferenzveröffentlichung
A1  - Schulder, Marc
A1  - Wiegand, Michael
A1  - Ruppenhofer, Josef
A1  - Roth, Benjamin
T1  - Towards Bootstrapping a Polarity Shifter Lexicon using Linguistic Features
T2  - Proceedings of the Eighth International Joint Conference on Natural Language Processing, November 27 - December 1, 2017, Taipei, Taiwan (Volume 1: Long Papers)
N2  - 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.
KW  - Computerlinguistik
KW  - Polarität
KW  - Natürliche Sprache
KW  - Maschinelles Lernen
KW  - Sentimentanalyse
Y1  - 2017
U6  - https://nbn-resolving.org/urn:nbn:de:bsz:mh39-84787
UN  - https://nbn-resolving.org/urn:nbn:de:bsz:mh39-84787
UR  - https://aclanthology.info/papers/I17-1063/i17-1063
SN  - 978-1-948087-00-1
SB  - 978-1-948087-00-1
SP  - 624
EP  - 633
PB  - Asian Federation of Natural Language Processing
CY  - Taipei
ER  -