Entity-Level Sentiment Analysis (ELSA): An exploratory task survey

TL;DR

This paper investigates the task of entity-level sentiment analysis in longer texts, revealing that existing sentiment analysis tasks do not adequately capture overall sentiment towards entities, and highlighting the need for specialized approaches.

Contribution

It introduces a new dataset for entity-level sentiment analysis in longer texts and evaluates the effectiveness of existing sentiment analysis levels for this task.

Findings

No single existing sentiment analysis task sufficiently captures entity sentiment.

Sentiment towards entities often involves relations beyond simple coreference.

Current models struggle to accurately determine overall entity sentiment in complex texts.

Abstract

This paper explores the task of identifying the overall sentiment expressed towards volitional entities (persons and organizations) in a document -- what we refer to as Entity-Level Sentiment Analysis (ELSA). While identifying sentiment conveyed towards an entity is well researched for shorter texts like tweets, we find little to no research on this specific task for longer texts with multiple mentions and opinions towards the same entity. This lack of research would be understandable if ELSA can be derived from existing tasks and models. To assess this, we annotate a set of professional reviews for their overall sentiment towards each volitional entity in the text. We sample from data already annotated for document-level, sentence-level, and target-level sentiment in a multi-domain review corpus, and our results indicate that there is no single proxy task that provides this overall sentiment we seek for the entities at a satisfactory level of performance. We present a suite of experiments aiming to assess the contribution towards ELSA provided by document-, sentence-, and target-level sentiment analysis, and provide a discussion of their shortcomings. We show that sentiment in our dataset is expressed not only with an entity mention as target, but also towards targets with a sentiment-relevant relation to a volitional entity. In our data, these relations extend beyond anaphoric coreference resolution, and our findings call for further research of the topic. Finally, we also present a survey of previous relevant work.