no code implementations • 10 Dec 2023 • Zening Duan, Anqi Shao, Yicheng Hu, Heysung Lee, Xining Liao, Yoo Ji Suh, Jisoo Kim, Kai-Cheng Yang, Kaiping Chen, Sijia Yang
Using moral content in tweets as a case study, we illustrate the steps to construct the moral foundations vec-tionary, showcasing its ability to process texts missed by conventional dictionaries and word embedding methods and to produce measurements better aligned with crowdsourced human assessments.
no code implementations • 27 Sep 2022 • Kaiping Chen, Anqi Shao, Jirayu Burapacheep, Yixuan Li
We traced these user experience divides to conversational differences and found that GPT-3 used more negative expressions when it responded to the education and opinion minority groups, compared to its responses to the majority groups.