Text Classification for Subjective Phenomena on Disaggregated Data and Rater Behaviour

Loading...
Thumbnail Image

Date

2023-04-22

Advisor

Journal Title

Journal ISSN

Volume Title

Publisher

Wydawnictwo Naukowe UAM

Title alternative

Abstract

Phenomena such as emotional experience and offensive language perception are highly subjective in nature. Yet, the dominant approach in building automatic emotion and hate speech detection systems is based on the opinion of the majority. Recently, however, a personalised or human-centred approach has been proposed by the computational social scientists. In the current paper, we propose a novel method for modelling individual perspective in emotion detection and abusive language recognition, following existing works in this area (Miłkowski et al., 2021). We show that the personalised approach that implements our Personalisation Metric (PM) outperforms traditional majority-based methods in regard to subjective phenomena such as emotion and abusive language detection. Proposed method could be successfully used in the development of more accurate classification models suitable for the opinions of individuals as well as in recommendation systems

Description

Sponsor

Keywords

emotion recognition, EDO 2023, human-centred NLP, offensive language

Citation

Gajewska E., Konat B. Text Classification for Subjective Phenomena on Disaggregated Data and Rater Behaviour. W: Human Language Technologies as a Challenge for Computer Science and Linguistics - 2023. Poznań: Wydawnictwo Naukowe UAM, 2023, pp. 73-78.

ISBN

978-83-232-4177-8

Title Alternative

Rights Creative Commons

Uniwersytet im. Adama Mickiewicza w Poznaniu
Biblioteka Uniwersytetu im. Adama Mickiewicza w Poznaniu
Ministerstwo Nauki i Szkolnictwa Wyższego