Personality Prediction Via Mono-Modal and Multi-Modal Information Analysis

Xiang Chen

doi:10.54097/6g3hcd40

Authors

Xiang Chen Art And Design College, Shenyang LiGong University, Shenyang,110000, China

DOI:

https://doi.org/10.54097/6g3hcd40

Keywords:

Personality Prediction; Unimodal Information; Mmultimodal Information; Text Analysis; Chart Analysis.

Abstract

Personality prediction has become an important part of the field where psychology and computer science meet. It is used for things like making suggestions, checking on mental health, and watching what people think about. Traditional assessment procedures such as questionnaires, interviews, etc. are limited by subjectivity, time consumption, scalability issues. With the rise of digital platforms, there’s been a ton of unstructured data—stuff like text and pictures and charts and sound—that’s showing up, allowing for actual computation methods when it comes to predicting personality. This paper is a review of personality prediction research between 2020 and 2025, including unimodal and multimodal methods. examines text-based kinds that extract linguistic features and chart-based sorts that look at behavioral and physiological patterns. Reviewing multiple modes which combine various data sources for improvement And also it talks about some mainstream datasets, current issues like data bias problems and data fusion difficulties are pointed out, suggestions for the future include developing cross-cultural datasets, using more advanced fusion algorithms and thinking about ethical factors. this overall summary can provide researchers who want to improve personality prediction technology and how it is used with a lot of useful ideas.

Downloads

Download data is not yet available.

References

[1] Bama S, Hema M S, Esakkirajan S, Nageswara Guptha M. A hierarchical transformer network with label attention for personality prediction by MBTI classification. Applied Soft Computing, 2025, 113267.

[2] Wu Q, Yu W, Chen J P. Fake news detection method based on personality prediction model. Data Analysis and Knowledge Discovery, 2025, 9(04): 123-133.

[3] Maharani W, Gani P H. Digital footprints and personality prediction: integrating methodological innovations and ethical considerations in social media analysis. Neural Computing and Applications, 2025: 1-44.

[4] Sun X, Huang J, Zheng S, Rao X, Wang M. Personality assessment based on multimodal attention network learning with category-based mean square error. IEEE Transactions on Image Processing, 2022, 31: 2162-2174.

[5] Zhao J, Zhao J, Chi C, Wang C, Zhao X, Jain A. Federated learning-inspired user personality prediction using sentiment analysis and topic preference. IEEE Transactions on Consumer Electronics, 2023, 70(1): 2729-2737.

[6] Guan Z M. Research and implementation of personality trait prediction based on social network text information. Beijing University of Posts and Telecommunications, 2021. DOI: 10.26969/d.cnki.gbydu.2021.001483.

[7] Kosan M A, Karacan H, Urgen B A. Personality traits prediction model from Turkish contents with semantic structures. Neural Computing and Applications, 2023, 35(23): 17147-17165.

[8] Ramezani M, Feizi-Derakhshi M R, Balafar M A. Knowledge graph-enabled text-based automatic personality prediction. Computational Intelligence and Neuroscience, 2022, 2022(1): 3732351.

[9] Ramezani M, Feizi-Derakhshi M R, Balafar M A. Text-based automatic personality prediction using KGrAt-Net: a knowledge graph attention network classifier. Scientific Reports, 2022, 12: 21453.

[10] Wang R, Zhao X, Xu X, et al. A multimodal personality prediction framework based on adaptive graph transformer network and multi-task learning. Computer Graphics Forum, 2025, 44(2): e70030-e70030.

[11] Jia X, Weijian T, Guoyun L, et al. Spatiotemporal fusion personality prediction based on visual information. Multimedia Tools and Applications, 2023, 82(28): 44227-44244.