Directed Social Regard: Surfacing Targeted Advocacy, Opposition, Aid, Harms, and Victimization in Online Media

2026-05-01

AI Summary

Existing sentiment analysis approaches struggle to simultaneously identify co-occurring prosocial and antisocial sentiments in text directed toward distinct targets. To address this limitation, this work proposes the Directed Social Regard (DSR) framework, which integrates theories of moral disengagement and moral foundations to construct a three-dimensional, multivalent sentiment representation. DSR introduces a Transformer-based architecture for span-level target detection and sentiment scoring, enabling the first fine-grained, multidimensional, valence-aware, and target-oriented analysis of social sentiments. Through a dedicated data collection and annotation strategy, DSR is validated on six third-party online media datasets, demonstrating strong associations between its outputs and established social science constructs and topics, thereby significantly advancing the modeling of complex social emotions.

Abstract

The language in online platforms, influence operations, and political rhetoric frequently directs a mix of pro-social sentiment (e.g., advocacy, helpfulness, compassion) and anti-social sentiment (e.g., threats, opposition, blame) at different topics, all in the same message. While many natural language processing (NLP) tools classify or score a text's overall sentiment as positive, neutral, or negative, these tools cannot report that positive and negative sentiments coexist, and they cannot report the target of those sentiments. This paper presents the Directed Social Regard (DSR) approach to multi-dimensional, multi-valence sentiment analysis, comprised of a pair of transformer-based models that (1) detects span-level targets of sentiment in a message and then (2) scores all spans within the message context along three (-1, 1) axes of regard that are motivated by social science theories of moral disengagement and moral framing. We present a data collection and annotation strategy for DSR dataset construction, a transformer-based architecture for span-level scoring, and a validation study with promising results. We apply the validated DSR model on six third-party datasets of online media and report meaningful correlations between DSR outputs and the labels and topics in these pre-existing social science datasets.

Problem

• sentiment analysis
• multi-valence sentiment
• targeted sentiment
• online media
• social regard

Innovation

• Directed Social Regard
• multi-valence sentiment analysis
• span-level target detection
• transformer-based models
• moral framing