Researcher Compass

Recently, Altmetric introduced a new Sentiment Analysis feature that uses artificial intelligence (AI) and a Large Language Model (LLM) to evaluate the tone of social media mentions related to research outputs. This feature assigns sentiment scores—from strongly negative to strongly positive—to social media posts, providing additional context beyond the mere volume of attention. Users can view these sentiment scores, explore sentiment trends over time, and filter mentions by sentiment category. This functionality aims to offer a more nuanced understanding of how research is received and discussed in public online spaces.

• -3 Strongly negative: Expresses strong criticism, warns against, or alerts about the mentioned paper.
• -2 Weak negative: Casts doubt, questions, cautions, or queries the research.
• -1 Uncertain negative: Includes satire, irony, humor, concern, or vague negative hints.
• 0 Neutral: Contains no sentiment towards the research, such as simply sharing a link or title.
• 1 Uncertain positive: For example, a human shares the title and link, possibly with a tag or hashtag.
• 2 Weak positive: Includes some commentary, suggests reading, or uses the research to support an argument without explicit praise.
• 3 Strong positive: Expresses strong recommendation, calls the research essential or a solution, or praises it as great work or evidence.

Source: Sentiment Analysis in Altmetric

CityUHK researchers can access Altmetric data through CityUHK Scholars by searching for research outputs and locating the Altmetric badge alongside records. Clicking the badge directs users to the Altmetric website where detailed information, including the new sentiment analysis, is available. Via the library's subscription to Altmetric Explorer, users can also perform advanced searches, save queries, generate reports, and incorporate sentiment filters to better analyze research impact.

For more information, view the Library Guides Retrieving Altmetric Details from CityUHK Scholars and Altmetric Explorer for CityUHK.