Summary of A Chinese Multi-label Affective Computing Dataset Based on Social Media Network Users, by Jingyi Zhou et al.
A Chinese Multi-label Affective Computing Dataset Based on Social Media Network Users
by Jingyi Zhou, Senlin Luo, Haofan Chen
First submitted to arxiv on: 13 Nov 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Computers and Society (cs.CY)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper addresses a significant gap in affective computing by collecting and annotating a large-scale Chinese dataset that integrates emotion and personality traits. The study draws on Weibo, a major social media platform, to gather data from over 50,000 individuals, screening out 11,338 valid users with diverse MBTI personality labels. The resulting dataset includes 566,900 posts, each annotated with intensity levels for six emotions and micro-emotions, as well as the user’s personality traits. The EQN method is used to compile this multi-label dataset, which demonstrates strong utility across multiple NLP classification models. This dataset has far-reaching implications for machine recognition of complex human emotions and can support research in psychology, education, marketing, finance, and politics. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper fills a big gap in understanding how people feel and behave online. Currently, there aren’t many datasets that show both how someone is feeling (emotion) and what kind of person they are (personality). In China, there’s an even bigger shortage of these kinds of datasets. To fix this, researchers collected data from Weibo, a popular social media site, and looked at 11,338 people who had diverse personalities. They got over 566,000 posts from these people, each labeled with how intense the emotions were and what kind of personality was behind them. This dataset is super useful for machines to understand human emotions better and can help researchers in many fields like psychology, education, marketing, finance, and politics. |
Keywords
» Artificial intelligence » Classification » Nlp
