Header

UZH-Logo

Maintenance Infos

Towards target-dependent sentiment classification in news articles


Hamborg, Felix; Donnay, Karsten; Gipp, Bela (2021). Towards target-dependent sentiment classification in news articles. In: Toeppe, Katharina; Yan, Hui; Chu, Samuel Kai Wah. Diversity, divergence, dialogue. Cham: Springer, 156-166.

Abstract

Extensive research on target-dependent sentiment classification (TSC) has led to strong classification performances in domains where authors tend to explicitly express sentiment about specific entities or topics, such as in reviews or on social media. We investigate TSC in news articles, a much less researched domain, despite the importance of news as an essential information source in individual and societal decision making. This article introduces NewsTSC, a manually annotated dataset to explore TSC on news articles. Investigating characteristics of sentiment in news and contrasting them to popular TSC domains, we find that sentiment in the news is expressed less explicitly, is more dependent on context and readership, and requires a greater degree of interpretation. In an extensive evaluation, we find that the current state-of-the-art in TSC performs worse on news articles than on other domains (average recall AvgRec=69.8 on NewsTSC compared to AvgRev=[75.6,82.2] on established TSC datasets). Reasons include incorrectly resolved relation of target and sentiment-bearing phrases and off-context dependence. As a major improvement over previous news TSC, we find that BERT’s natural language understanding capabilities capture the less explicit sentiment used in news articles.

Abstract

Extensive research on target-dependent sentiment classification (TSC) has led to strong classification performances in domains where authors tend to explicitly express sentiment about specific entities or topics, such as in reviews or on social media. We investigate TSC in news articles, a much less researched domain, despite the importance of news as an essential information source in individual and societal decision making. This article introduces NewsTSC, a manually annotated dataset to explore TSC on news articles. Investigating characteristics of sentiment in news and contrasting them to popular TSC domains, we find that sentiment in the news is expressed less explicitly, is more dependent on context and readership, and requires a greater degree of interpretation. In an extensive evaluation, we find that the current state-of-the-art in TSC performs worse on news articles than on other domains (average recall AvgRec=69.8 on NewsTSC compared to AvgRev=[75.6,82.2] on established TSC datasets). Reasons include incorrectly resolved relation of target and sentiment-bearing phrases and off-context dependence. As a major improvement over previous news TSC, we find that BERT’s natural language understanding capabilities capture the less explicit sentiment used in news articles.

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Downloads

35 downloads since deposited on 07 Oct 2021
10 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Book Section, refereed, original work
Communities & Collections:06 Faculty of Arts > Institute of Political Science
08 Research Priority Programs > Digital Society Initiative
Dewey Decimal Classification:320 Political science
Scopus Subject Areas:Physical Sciences > Theoretical Computer Science
Physical Sciences > General Computer Science
Uncontrolled Keywords:sentiment classification, stance detection, news bias, media bias
Language:English
Date:19 March 2021
Deposited On:07 Oct 2021 16:37
Last Modified:18 Mar 2024 04:43
Publisher:Springer
ISBN:978-3-030-71292-1
Additional Information:16th International Conference, iConference 2021, Beijing, China, March 17–31, 2021, Proceedings
OA Status:Green
Free access at:Publisher DOI. An embargo period may apply.
Publisher DOI:https://doi.org/10.1007/978-3-030-71305-8_12
  • Content: Published Version
  • Language: English
  • Licence: Creative Commons: Attribution-NonCommercial-ShareAlike 1.0 Generic (CC BY-NC-SA 1.0)