Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
60 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
8 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Is ChatGPT a Good Personality Recognizer? A Preliminary Study (2307.03952v3)

Published 8 Jul 2023 in cs.CL

Abstract: In recent years, personality has been regarded as a valuable personal factor being incorporated into numerous tasks such as sentiment analysis and product recommendation. This has led to widespread attention to text-based personality recognition task, which aims to identify an individual's personality based on given text. Considering that ChatGPT has recently exhibited remarkable abilities on various natural language processing tasks, we provide a preliminary evaluation of ChatGPT on text-based personality recognition task for generating effective personality data. Concretely, we employ a variety of prompting strategies to explore ChatGPT's ability in recognizing personality from given text, especially the level-oriented prompting strategy we designed for guiding ChatGPT in analyzing given text at a specified level. The experimental results on two representative real-world datasets reveal that ChatGPT with zero-shot chain-of-thought prompting exhibits impressive personality recognition ability and is capable to provide natural language explanations through text-based logical reasoning. Furthermore, by employing the level-oriented prompting strategy to optimize zero-shot chain-of-thought prompting, the performance gap between ChatGPT and corresponding state-of-the-art model has been narrowed even more. However, we observe that ChatGPT shows unfairness towards certain sensitive demographic attributes such as gender and age. Additionally, we discover that eliciting the personality recognition ability of ChatGPT helps improve its performance on personality-related downstream tasks such as sentiment classification and stress prediction.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (75)
  1. Personality traits. General psychology: Required reading, 278, 2019.
  2. Motivating personality-aware machine translation. In Empirical Methods in Natural Language Processing, pages 1102–1108, 2015.
  3. Personalized machine translation: Preserving original author traits. In European Chapter of the Association for Computational Linguistics, volume 1, pages 1074–1084, 2017.
  4. An emotion-based personalized music recommendation framework for emotion improvement. Information Processing & Management, 60(3):103256, 2023.
  5. “knowing me, knowing you”: personalized explanations for a music recommender system. User Modeling and User-Adapted Interaction, 32(1-2):215–252, 2022.
  6. Personality-based refinement for sentiment classification in microblog. Knowledge-Based Systems, 132:204–214, 2017.
  7. Automatic prediction of depression and anxiety from behaviour and personality attributes. In Affective Computing and Intelligent Interaction, pages 1–7, 2019.
  8. A novel personality detection method based on high-dimensional psycholinguistic features and improved distributed gray wolf optimizer for feature selection. Information Processing & Management, 60(2):103217, 2023.
  9. Contrastive graph transformer network for personality detection. In International Joint Conference on Artificial Intelligence, pages 4559–4565, 2022.
  10. A lexical psycholinguistic knowledge-guided graph neural network for interpretable personality detection. Knowledge-Based Systems, 249:108952, 2022.
  11. Jacob Devlin Ming-Wei Chang Kenton and Lee Kristina Toutanova. Bert: Pre-training of deep bidirectional transformers for language understanding. In North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4171–4186, 2019.
  12. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692, 2019.
  13. Language models are few-shot learners. Neural Information Processing Systems, 33:1877–1901, 2020.
  14. Pathways language model (palm): Scaling to 540 billion parameters for breakthrough performance, 2022.
  15. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971, 2023.
  16. Personality bert: A transformer-based model for personality detection from textual data. In International Conference on Computing and Communication Networks, pages 515–522, 2022.
  17. Personality classification based on bert model. In International Conference on Emergency Science and Information Technology, pages 150–152, 2021.
  18. Is chatgpt a general-purpose natural language processing task solver? arXiv preprint arXiv:2302.06476, 2023.
  19. Is chatgpt good at search? investigating large language models as re-ranking agent. arXiv preprint arXiv:2304.09542, 2023.
  20. Is chatgpt a good nlg evaluator? a preliminary study. arXiv preprint arXiv:2303.04048, 2023.
  21. Is chatgpt a good translator? a preliminary study. arXiv preprint arXiv:2301.08745, 2023.
  22. Is chatgpt a good recommender? a preliminary study. arXiv preprint arXiv:2304.10149, 2023.
  23. On the evaluations of chatgpt and emotion-enhanced prompting for mental health analysis. arXiv preprint arXiv:2304.03347, 2023.
  24. Neural sentiment classification with user and product attention. In Empirical Methods in Natural Language Processing, pages 1650–1659, 2016.
  25. Distributed representations of sentences and documents. In International Conference on Machine Learning, pages 1188–1196, 2014.
  26. A hybrid e-learning recommendation integrating adaptive profiling and sentiment analysis. Journal of Web Semantics, 72:100700, 2022.
  27. Large-scale relation extraction from web documents and knowledge graphs with human-in-the-loop. Journal of Web Semantics, 60:100546, 2020.
  28. Is big five better than mbti? a personality computing challenge using twitter data. In Italian Conference on Computational Linguistics, 2018.
  29. John M Digman. Personality structure: Emergence of the five-factor model. Annual Review of Psychology, 41(1):417–440, 1990.
  30. David J Pittenger. Measuring the mbti… and coming up short. Journal of Career Planning and Employment, 54(1):48–52, 1993.
  31. Gregory J Boyle. Myers-briggs type indicator (mbti): some psychometric limitations. Australian Psychologist, 30(1):71–74, 1995.
  32. David J Pittenger. Cautionary comments regarding the myers-briggs type indicator. Consulting Psychology Journal: Practice and Research, 57(3):210, 2005.
  33. Knowledge-enhanced multi-task learning for course recommendation. In International Conference on Database Systems for Advanced Applications, pages 85–101, 2022.
  34. Personalizing recommendation diversity based on user personality. User Modeling and User-Adapted Interaction, 28(3):237–276, 2018.
  35. Beyond the big five personality traits for music recommendation systems. EURASIP Journal on Audio, Speech, and Music Processing, 2023(1):4, 2023.
  36. Recommendation model for tourism by personality type using mass diffusion method. In Human-Computer Interaction, pages 80–95, 2022.
  37. PT Costa and RR McCrae. Neo five-factor inventory (neo-ffi). Odessa, FL: Psychological Assessment Resources, 3, 1989.
  38. Oliver P John. The big five inventory—versions 4a and 54. (No Title), 1991.
  39. Measuring personality in one minute or less: A 10-item short version of the big five inventory in english and german. Journal of Research in Personality, 41(1):203–212, 2007.
  40. Analyzing personality related adjectives from an eticemic perspective: the big five marker scales (bfms) and the italian ab5c taxonomy. Big Five Assessment, pages 281–304, 2002.
  41. Knowledge of words: An interpretable approach for personality recognition from social media. Knowledge-Based Systems, 194:105550, 2020.
  42. Facial-based personality prediction models for estimating individuals private traits. In International Conference on Parallel & Distributed Processing with Applications, Big Data & Cloud Computing, Sustainable Computing & Communications, Social Computing & Networking, pages 1586–1594, 2019.
  43. Predicting the big five personality traits from handwriting. EURASIP Journal on Image & Video Processing, 2018:1–17, 2018.
  44. Human personality identification based on handwriting analysis. In International Conference on Advances in Science and Technology, pages 393–398, 2022.
  45. Automatic personality prediction based on users’ chinese handwriting change. In CCF Conference on Computer Supported Cooperative Work and Social Computing, pages 435–449, 2023.
  46. Automatic children’s personality assessment from emotional speech. Expert Systems with Applications, 187:115885, 2022.
  47. Speech-based automatic personality trait prediction analysis. International Journal of Advanced Intelligence Paradigms, 17(1-2):91–108, 2020.
  48. Eeg-based personality prediction using fast fourier transform and deeplstm model. Computational Intelligence and Neuroscience, 2021:1–10, 2021.
  49. Quantitative personality predictions from a brief eeg recording. Affective Computing, 13(03):1514–1527, 2022.
  50. Automatic personality assessment through social media language. Journal of Personality and Social Psychology, 108(6):934, 2015.
  51. Language style matching in writing: synchrony in essays, correspondence, and poetry. Journal of Personality and Social Psychology, 99(3):549, 2010.
  52. The development and psychometric properties of liwc2015. Technical report, 2015.
  53. Personality prediction system from facebook users. Procedia Computer Science, 116:604–611, 2017.
  54. Structured programming for linguistic cue extraction (splice). In HICSS-45 Rapid Screening Technologies, Deception Detection and Credibility Assessment Symposium, pages 103–108, 2012.
  55. Personality predictions based on user behavior on the facebook social media platform. IEEE Access, 6:61959–61969, 2018.
  56. Deep learning-based document modeling for personality detection from text. IEEE Intelligent Systems, 32(2):74–79, 2017.
  57. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781, 2013.
  58. Deep learning-based personality recognition from text posts of online social networks. Applied Intelligence, 48:4232–4246, 2018.
  59. Hierarchical modeling for user personality prediction: The role of message-level attention. In Association for Computational Linguistics, pages 5306–5316, 2020.
  60. How to fine-tune bert for text classification? In Chinese Computational Linguistics, pages 194–206, 2019.
  61. Predictive intelligence in harmful news identification by bert-based ensemble learning model with text sentiment analysis. Information Processing & Management, 59(2):102872, 2022.
  62. An enhanced guided lda model augmented with bert based semantic strength for aspect term extraction in sentiment analysis. Knowledge-Based Systems, 246:108668, 2022.
  63. Bottom-up and top-down: Predicting personality with psycholinguistic and language model features. In International Conference on Data Mining, pages 1184–1189, 2020.
  64. A sentiment-aware deep learning approach for personality detection from text. Information Processing & Management, 58(3):102532, 2021.
  65. Linguistic styles: language use as an individual difference. Journal of Personality and Social Psychology, 77(6):1296, 1999.
  66. Multimodal personality trait recognition using wearable sensors in response to public speaking. IEEE Sensors Journal, 20(12):6532–6541, 2020.
  67. Deep learning based personality recognition from facebook status updates. In international Conference on Awareness Science and Technology, pages 383–387, 2017.
  68. Glove: Global vectors for word representation. In Empirical Methods in Natural Language Processing, pages 1532–1543, 2014.
  69. Automatic text-based personality recognition on monologues and multiparty dialogues using attentive networks and contextual embeddings (student abstract). In Association for the Advancement of Artificial Intelligence, volume 34, pages 13821–13822, 2020.
  70. A review on evaluation metrics for data classification evaluations. International Journal of Data Mining & Knowledge Management Process, 5(2):1, 2015.
  71. Is chatgpt fair for recommendation? evaluating fairness in large language model recommendation. arXiv preprint arXiv:2305.07609, 2023.
  72. Age and gender differences in motivational manifestations of the big five from age 16 to 60. Developmental Psychology, 49(2):365, 2013.
  73. Emotion. 2011.
  74. Symptoms of anxiety and depression in medical students and in humanities students: relationship with big-five personality dimensions and vulnerability to stress. International Journal of Social Psychiatry, 54(6):494–501, 2008.
  75. Character-level convolutional networks for text classification. Neural Information Processing Systems, 28, 2015.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Yu Ji (28 papers)
  2. Wen Wu (103 papers)
  3. Hong Zheng (33 papers)
  4. Yi Hu (129 papers)
  5. Xi Chen (1035 papers)
  6. Liang He (202 papers)
Citations (20)
View on Semantic Scholar
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets