Description: How accurately do you think you could predict peoples’ Big Fiver personality profiles by reviewing their twitter posts? Really, pick a percentage! Are peoples’ Twitter personalities different than those they show in face-to-face interactions? Now, with your number picked (assuming it was not a zero), think about what you would look for in your analyses of peoples’ twitter posts that would allow you to predict their location on each of the 5 dimensions that make up the Big Five personality model (Openness to Experience, Conscientiousness, Extroversion, Agreeableness, and Stability (Neuroticism). Once you have your method worked out have a read through the article linked below that describes a study that tried to do the same thing.
Source: An individual’s personality appears to be correlated with their Twitter behavior, Emily Manis, PsyPost.
Date: April 13, 2022
Did the 75% accuracy surprise you or were you thinking that Twitter interaction is still social interaction so maybe there should be a strong relationship? Did the follower data make sense – more followers = more aggregable and more extroverted – fewer followers = more neurotic (unstable)? Finally, did the linked article seem a bit thin on its description of what the researchers did? If not you can see read the actual research article via the link in the Further Reading section below. This is something you will certainly have to do before you are able to judge the validity of the researchers’ second to last sentence in their journal article: “Overall, the study provides a deep insight into the impact of social media in providing predictive indicators of user behavior.” I would suggest that more reading is required before you can decide if more research in required in this area.
Questions for Discussion:
- How are Twitter posts and personality profiles possibly related?
- Didi the results described in the posted article make sense?
- Could you speak to the validity of the research articles closing statement, quoted above, based on the description of the research reported upon in the linked article, if not what else would you need in order to be able to offer a response?
References (Read Further):
Mahajan, R., Mahajan, R., Sharma, E., & Mansotra, V. (2022). “Are we tweeting our real selves?” personality prediction of Indian Twitter users using deep learning ensemble model. Computers in Human Behavior, 128, 107101. Link
Peterka‐Bonetta, J., Sindermann, C., Elhai, J. D., & Montag, C. (2021). How objectively measured Twitter and Instagram use relate to self‐reported personality and tendencies toward Internet/Smartphone Use Disorder. Human Behavior and Emerging Technologies, 3(5), 898-911. Link
Usselmann, H., Ahmad, R., & Siemon, D. (2021). A Personality Mining System for German Twitter Posts With Global Vectors Word Embedding. IEEE Access, 9, 165576-165610. Link
Yun, J. T., Pamuksuz, U., & Duff, B. R. (2019). Are we who we follow? Computationally analyzing human personality and brand following on Twitter. International Journal of Advertising, 38(5), 776-795. Link
Kunte, A. V., & Panicker, S. (2019, November). Using textual data for personality prediction: a machine learning approach. In 2019 4th international conference on information systems and computer networks (ISCON) (pp. 529-533). IEEE. Link
Carducci, G., Rizzo, G., Monti, D., Palumbo, E., & Morisio, M. (2018). Twitpersonality: Computing personality traits from tweets using word embeddings and supervised learning. Information, 9(5), 127. Link
Malik, A., Heyman-Schrum, C., & Johri, A. (2019). Use of Twitter across educational settings: a review of the literature. International Journal of Educational Technology in Higher Education, 16(1), 1-22. Link
Vallée, J. (2018). Urban isolation and daytime neighborhood social composition from Twitter data. Proceedings of the National Academy of Sciences, 115(51), E11886-E11887. Link