Skip to content

Read-only version: For security reasons, the Research Information System (FIS) has been temporarily replaced by this read-only version. All public content and full texts remain available; login, editing, submission and statistics are not available. Questions: fis@uni-bamberg.de

Home › Publications › Entity-Level Sentiment : More than the Sum of Its Parts

Publication

Entity-Level Sentiment : More than the Sum of Its Parts

Rønningstad, Egil; Klinger, Roman; Øvrelid, Lilja; u. a. (2024): Entity-Level Sentiment : More than the Sum of Its Parts, in: Orphée De Clercq, Valentin Barriere, Jeremy Barnes, u. a. (Hrsg.), Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis, Bangkok, Thailand: Association for Computational Linguistics, S. 84–96, doi: 10.18653/v1/2024.wassa-1.8.

Details

Faculty/Chair
Faculty/Professorship
Author
Rønningstad, Egil
Øvrelid, Lilja
Velldal, Erik
Title of the compilation
Proceedings of the 14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis
Editors
De Clercq, Orphée
Barriere, Valentin
Barnes, Jeremy
Sedoc, João
Tafreshi, Shabnam
Conference
14th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis, Bangkok, Thailand
Publisher Information
Association for Computational Linguistics : Bangkok, Thailand
Year of publication
2024
Language
English
DOI
URL
Abstract

In sentiment analysis of longer texts, there may be a variety of topics discussed, of entities mentioned, and of sentiments expressed regarding each entity. We find a lack of studies exploring how such texts express their sentiment towards each entity of interest, and how these sentiments can be modelled. In order to better understand how sentiment regarding persons and organizations (each entity in our scope) is expressed in longer texts, we have collected a dataset of expert annotations where the overall sentiment regarding each entity is identified, together with the sentence-level sentiment for these entities separately. We show that the reader’s perceived sentiment regarding an entity often differs from an arithmetic aggregation of sentiments at the sentence level. Only 70% of the positive and 55% of the negative entities receive a correct overall sentiment label when we aggregate the (human-annotated) sentiment labels for the sentences where the entity is mentioned. Our dataset reveals the complexity of entity-specific sentiment in longer texts, and allows for more precise modelling and evaluation of such sentiment expressions.

Keywords
Entity-Level Sentiment
Peer Reviewed
yes
International Distribution
yes
Open Access Journal
yes
Type
Conferenceobject
URI
Activation date
2024-09-20

Permalink: https://fis.uni-bamberg.de/handle/uniba/98198 · Data as JSON · Cite: BibTeX · RIS

Data as of: 2026-11-15

Restricted read-only access: login, editing and submission are temporarily disabled.