AudienceView: AI-Assisted Interpretation of Audience Feedback in Journalism

TL;DR

AudienceView is introduced, an online tool to help journalists categorize and interpret audience feedback by leveraging large language models (LLMs) and it is considered how such tools can be useful in a journalist's workflow, and the importance of contextual awareness and human judgment.

Abstract

Understanding and making use of audience feedback is important but difficult for journalists, who now face an impractically large volume of audience comments online. We introduce AudienceView, an online tool to help journalists categorize and interpret this feedback by leveraging large language models (LLMs). AudienceView identifies themes and topics, connects them back to specific comments, provides ways to visualize the sentiment and distribution of the comments, and helps users develop ideas for subsequent reporting projects. We consider how such tools can be useful in a journalist's workflow, and emphasize the importance of contextual awareness and human judgment.

Figures (2)

• Figure 1: Selected views of the app interface: a video-level dashboard of comments, and channel-level generated themes.
• Figure 2: The topics detected in channel-wide comments.