Elamur Research⌕
☰
home / papers / 2024 / Personality Analysis for Social Media Users using Arabic language and its Effect on Sentiment Analysis

Personality Analysis for Social Media Users using Arabic language and its Effect on Sentiment Analysis

Summary

The paper asks whether Arabic-language Twitter activity can reveal a user's personality type, and whether personality changes the sentiment people express online. Arabic is under-studied here: its morphology is rich, diacritics are usually omitted, and many dialects lack standard spelling. The authors found users who took the Arabic version of the 16personalities (MBTI-style) test and then posted their result on Twitter. They crawled the profiles and timelines of these users to build a corpus called "AraPers" with 3,250 people. They ran statistical comparisons using linguistic cues, profile attributes (gender, age, bio), emoticons and interaction counts. They also trained several machine-learning classifiers on a version of the data with an equal number of tweets per type. BERT performed best, at 74.86% accuracy. A separate sentiment classifier, applied per personality type, showed different positive, negative and neutral shares across types. The work matters because it gives Arabic a sizable personality-labelled resource. It also links user traits to sentiment, which is relevant to opinion tracking and political discourse analysis.

Key points

  • Dataset "AraPers" covers 3,250 Twitter users whose labels come from their own shared results on 16personalities.com/ar (16 MBTI types, four opposed axes: E/I, S/N, T/F, J/P).
  • The features combine tweet language, profile statistics (gender, age, bio, etc.), emoticons, and interactions such as retweets and replies.
  • The best personality model was BERT, at 74.86% accuracy. Models were trained on a "Balanced Corpus" with equal tweet counts per type.
  • Sentiment was labelled by a logistic regression model trained on 14,744 tagged tweets, with three classes: positive, negative and neutral.
  • ESFJ and ESTP had the most positive tweets, INFJ and ISTJ the most negative, and ESTJ and ENTJ the most neutral. By axis, E/S/F leaned positive, I/P/N leaned negative, and J/T leaned neutral. The authors flag self-selection, cultural and socioeconomic bias in their sample.

Interesting ideas

  • I1. Self-disclosed labels: Labels are harvested from users who voluntarily publish a standardized test outcome, which avoids hand annotation while keeping a fixed label scheme. — For Mova (learn): We could mine texts where authors explicitly state a fact about their own content (e.g. "the answer is X") as cheap silver labels. These labels should be cross-checked by witness parsers before use.
  • I2. Balanced comparisons: The data is equalized to the same number of tweets per class before training or comparing groups, so differences are not artifacts of class size. — For Mova (learn): Evaluation suites could be balanced per construction or frame type, so that a frequent phenomenon cannot mask regressions on rare ones.
  • I3. Factorized labels: A 16-way label is broken into four binary axes, and results are reported per axis, which yields interpretable trends instead of 16 noisy cells. — For Mova (frames): Speech-act or stance labels could be decomposed into independent dimensions (e.g. assertive vs directive, polite vs blunt), so each decision stays separately explainable.
  • I4. Classifier as a probe: An existing sentiment model is used as a measuring instrument over labelled populations, and its output distributions are compared per group rather than its accuracy. — For Mova (learn): A fixed tagger or parser could be run over different genres (fables, school tests, word problems), comparing label distributions to spot domain shift before it hurts answers.
  • I5. Naming sampling bias: The authors state openly that volunteers who disclose results are not a representative sample, and they treat this as a limit on validity. — For Mova (learn): Silver data built only from sentences that all witnesses agree on is likewise biased toward easy cases. Negative controls should include the hard sentences that the agreement filter discards.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Cited by

2 papers of our library cite it (of the 140884 whose bibliographies we read); 1 of them have a page here, 1 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.48550/arxiv.2407.06314 · arXiv 2407.06314

@misc{dandash2024personality,
  title = {{Personality Analysis for Social Media Users using Arabic language and its Effect on Sentiment Analysis}},
  author = {Dandash, Mokhaiber and Asadpour, Masoud},
  year = {2024},
  doi = {10.48550/arxiv.2407.06314},
  eprint = {2407.06314},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2407.06314}
}

References

54 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Dandash, M., & Asadpour, M. (2023). Recognizing personality traits using Twitter & Facebook for Arabic speaking users in Lebanon. Inernational Journal of Information and Communication Technology Research, 15(1), 45-55. https://doi.org/10.61186/itrc.15.1.45 ↗
  2. McKenna, K. Y. A., Green, A. S., & Gleason, M. E. J. (2002). Relationship formation on the Internet: What’s the big attraction? Journal of Social Issues, 58(1), 9–31. https://doi.org/10.1111/1540-4560.00246 ↗
  3. Gosling, S. D., Augustine, A. A., Vazire, S., Holtzman, N., & Gaddis, S. (2011). Manifestations of personality in online social networks: Self-reported Facebook-related behaviors and observable profile information. Cyberpsychology, Behavior, and Social Networking, 14(9), 483–488. https://doi.org/10.1089/cyber.2010.0087 ↗
  4. Cervone, D., & Pervin, L. A. (2015). Personality: Theory and research. John Wiley & Sons. find
  5. Alexa. (2017). The top 500 sites on the web. Alexa Internet. Retrieved March 28, 2017, from https://www.alexa.com/topsites ↗
  6. Shirky, C. (2011). The political power of social media: Technology, the public sphere, and political change. Foreign Affairs, 90(1), 28–41. Retrieved from https://www.jstor.org/stable/25800379 ↗
  7. Carpenter, C. J. (2012). Narcissism on Facebook: Self-promotional and anti-social behavior. Personality and Individual Differences, 52(4), 482–486. https://doi.org/10.1016/j.paid.2011.11.011 ↗
  8. Correa, T., Hinsley, A. W., & Gil de Zúñiga, H. (2010). Who interacts on the Web? The intersection of users’ personality and social media use. Computers in Human Behavior, 26(2), 247–253. https://doi.org/10.1016/j.chb.2009.09.003 ↗
  9. Dupuis, M., Khadeer, S., & Huang, J. (2017). "I Got the Job!" An exploratory study examining the psychological factors related to status updates on Facebook. Computers in Human Behavior, 73, 132–140. https://doi.org/10.1016/j.chb.2017.03.020 ↗
  10. Schwartz, H. A., Eichstaedt, J. C., Kern, M. L., Dziurzynski, L., Ramones, S. M., Agrawal, M., … & Ungar, L. H. (2013). Personality, gender, and age in the language of social media: The open-vocabulary approach. PloS One, 8(9), e73791. https://doi.org/ 10.1371/journal.pone.0073791 ↗
  11. Wang, D. (2017). A study of the relationship between narcissism, extraversion, drive for entertainment, and narcissistic behavior on social networking sites. Computers in Human Behavior, 66, 138–148. https://doi.org/10.1016/j.chb.2016.09.036 ↗
  12. Caplan, S. E. (2006). Relations among loneliness, social anxiety, and problematic Internet use. CyberPsychology & Behavior, 10(2), 234–242. https://doi.org/10.1089/cpb.2006.9963 ↗
  13. Finn, S. (1997). Origins of media exposure: Linking personality traits to TV, radio, print, and film use. Communication Research, 24(5), 507–529. https://doi.org/10.1177/009365097024005003 ↗
  14. Kim, H. K., & Davis, K. E. (2009). Toward a comprehensive theory of problematic Internet use: Evaluating the role of self-esteem, anxiety, flow, and the self-rated importance of Internet activities. Computers in Human Behavior, 25(2), 490–500. https://doi.org/10.1016/j.chb.2008.11.001 ↗
  15. Moody, E. J. (2001). Internet use and its relationship to loneliness. CyberPsychology & Behavior, 4(3), 393–401. https://doi.org/10.1089/109493101300210303 ↗
  16. Qiu, L., Lin, H., Ramsay, J., & Yang, F. (2012). You are what you tweet: Personality expression and perception on Twitter. Journal of Research in Personality, 46(6), 710–718. https://doi.org/10.1016/j.jrp.2012.08.008 ↗
  17. Park, G., Schwartz, H. A., Eichstaedt, J. C., Kern, M. L., Kosinski, M., Stillwell, D. J., Ungar, L. H., & Seligman, M. E. P. (2015). Automatic personality assessment through social media language. Journal of Personality and Social Psychology, 108(6), 934–952. https://doi.org/10.1037/pspp0000020 ↗
  18. Koban, K., Stein, J.-P., Eckhardt, V., & Ohler, P. (2018). Quid pro quo in Web 2.0: Connecting personality traits and Facebook usage intensity to uncivil commenting intentions in public online discussions. Computers in Human Behavior, 79, 9–18. https://doi.org/10.1016/j.chb.2017.10.015 ↗
  19. Cassidy, J., Sherman, L. J., & Jones, J. D. (2012). What’s in a word? Linguistic characteristics of adult attachment interviews. Attachment & Human Development, 14(1), 11–32. https://doi.org/10.1080/14616734.2012.636649 ↗
  20. Lin, J., Mao, W., & Zeng, D. D. (2017). Personality-based refinement for sentiment classification in microblog. Knowledge-Based Systems, 132, 204–214. https://doi.org/10.1016/j.knosys.2017.06.031 ↗
  21. Orehek, E., & Human, L. J. (2017). Self-expression on social media: Do tweets present accurate and positive portraits of impulsivity, self-esteem, and attachment style? Personality and Social Psychology Bulletin, 43(1), 60–70. https://doi.org/10.1177/0146167216675332 ↗
  22. Adali, S., & Golbeck, J. (2012). Predicting personality with social behavior. In 2012 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (pp. 302–309). IEEE. https://doi.org/10.1109/ASONAM.2012.58 ↗
  23. Arnoux, P.-H., Xu, A., Boyette, N., Mahmud, J., Akkiraju, R., & Sinha, V. (2017). 25 tweets to know you: A new model to predict personality with social media. In 11th International AAAI Conference on Web and Social Media. https://doi.org/10.1609/icwsm.v11i1.14963 ↗
  24. Celli, F., Ghosh, A., Alam, F., & Riccardi, G. (2016). In the mood for sharing contents: Emotions, personality and interaction styles in the diffusion of news. Information Processing & Management, 52(1), 93–98. https://doi.org/10.1016/j.ipm.2015.08.002 ↗
  25. Golbeck, J., Robles, C., Edmondson, M., & Turner, K. (2011). Predicting personality from Twitter. In Privacy, Security, Risk and Trust (PASSAT) and 2011 IEEE Third International Conference on Social Computing (SocialCom) (pp. 149–156). IEEE. https://doi.org/10.1109/PASSAT/SocialCom.2011.33 ↗
  26. Lima, A. C. E. S., & De Castro, L. N. (2014). A multi-label, semi-supervised classification approach applied to personality prediction in social media. Neural Networks, 58, 122–130. https://doi.org/10.1016/j.neunet.2014.05.020 ↗
  27. Markovikj, D., Gievska, S., Kosinski, M., & Stillwell, D. (2013). Mining Facebook data for predictive personality modeling. In 7th International AAAI Conference on Weblogs and Social Media. https://doi.org/10.1609/icwsm.v7i2.14466 ↗
  28. Quercia, D., Kosinski, M., Stillwell, D., & Crowcroft, J. (2011). Our Twitter profiles, our selves: Predicting personality with Twitter. In 2011 IEEE Third International Conference on Privacy, Security, Risk and Trust and 2011 IEEE Third International Conference on Social Computing (pp. 180–185). https://doi.org/10.1109/PASSAT/SocialCom.2011.26 ↗
  29. Souri, A., Hosseinpour, S., & Rahmani, A. M. (2018). Personality classification based on profiles of social networks’ users and the five-factor model of personality. Human-centric Computing and Information Sciences, 8(1), 1–15. https://doi.org/10.1186/s13673-018-0147-4 ↗
  30. Tandera, T., Suhartono, D., Wongso, R., & Prasetio, Y. L. (2017). Personality prediction system from Facebook users. Procedia Computer Science, 116, 604–611. https://doi.org/10.1016/j.procs.2017.10.016 ↗
  31. Verhoeven, B., Daelemans, W., & De Smedt, T. (2013). Ensemble methods for personality recognition. In 7th International AAAI Conference on Weblogs and Social Media. https://doi.org/10.1609/icwsm.v7i2.14465 ↗
  32. Tadesse, M. M., Lin, H., Xu, B., & Yang, L. (2018). Personality predictions based on user behavior on the Facebook social media platform. IEEE Access, 6, 61959–61969. https://doi.org/10.1109/ACCESS.2018.2876502 ↗
  33. Wang, S., Cui, L., Liu, L., Lu, X., & Li, Q. (2020). Personality traits prediction based on users’ digital footprints in social networks via attention RNN. In 2020 IEEE International Conference on Services Computing (SCC’20) (pp. 54–56). IEEE. https://doi.org/10.1109/SCC49832.2020.00015 ↗
  34. Zhao, J., Zeng, D., Xiao, Y., Che, L., & Wang, M. (2020). User personality prediction based on topic preference and sentiment analysis using LSTM model. Pattern Recognition Letters, 138, 397–402. https://doi.org/10.1016/j.patrec.2020.07.035 ↗
  35. Habash, N. Y. (2010). Introduction to Arabic natural language processing. Synthesis Lectures on Human Language Technologies, 3(1), 1–187. find
  36. Liu, L., Preotiuc-Pietro, D., Samani, Z. R., Moghaddam, M. E., & Ungar, L. Analyzing personality through social media profile picture choice. https://doi.org/10.1609/icwsm.v10i1.14738 ↗
  37. Sumner, C., Byers, A., Boochever, R., & Park, G. J. (2012). Predicting dark triad personality traits from Twitter usage and a linguistic analysis of tweets. In 2012 11th International Conference on Machine Learning and Applications (ICMLA) (Vol. 2, pp. 386– 393). IEEE. https://doi.org/10.1109/ICMLA.2012.218 ↗
  38. Schwartz, H. A., Eichstaedt, J. C., Dziurzynski, L., Kern, M. L., Seligman, M. E. P., Ungar, L. H., Blanco, E., Kosinski, M., & Stillwell, D. (2013). Toward personality insights from language exploration in social media. AAAI Spring Symposium Series. https://doi.org/10.1371/journal.pone.0073791 ↗
  39. Farnadi, G., Zoghbi, S., Moens, M.-F., & De Cock, M. (2013). Recognizing personality traits using Facebook status updates. Seventh International AAAI Conference on Weblogs and Social Media. https://doi.org/10.1609/icwsm.v7i2.14470 ↗
  40. Celli, F., Pianesi, F., Stillwell, D., & Kosinski, M. (2013). Workshop on Computational Personality Recognition: Shared Task. Seventh International AAAI Conference on Weblogs and Social Media. https://doi.org/10.1609/icwsm.v7i2.14467 ↗
  41. Peats.de. (n.d.). Big Five - die Persönlichkeit in fünf Dimensionen. Retrieved October 28, 2021, from https://peats.de/article/big-five-die-personlichkeit-in-funf-dimensionen ↗
  42. Myers, I. B., & Myers, P. B. (1995). Gifts differing: Understanding personality type. Davies-Black Publishing. find
  43. The Myers & Briggs Foundation. (n.d.). MBTI® Basics. Retrieved October 28, 2021, from https://www.myersbriggs.org/my-mbti-personality-type/mbti-basics/ ↗
  44. The Myers & Briggs Company. (n.d.). Myers-Briggs Type Indicator® (MBTI®) | Official Myers Briggs Personality Test. Retrieved October 28, 2021, from https://www.themyersbriggs.com/ ↗
  45. Huber, D., Kaufmann, H., & Steinmann, M. (2017). The missing link: The innovation gap. In Bridging the Innovation Gap (pp. 21– 41). Springer International Publishing. https://doi.org/10.1007/978-3-319-55498-3_3 ↗
  46. Isaak, J., & Hana, M. J. (2018). User data privacy: Facebook, Cambridge Analytica, and privacy protection. IEEE Computer, 51. https://doi.org/10.1109/MC.2018.3191268 ↗
  47. McPherson, M., Smith-Lovin, L., & Cook, J. M. (2001). Birds of a feather: Homophily in social networks. Annual Review of Sociology, 27, 415-444. https://doi.org/10.1146/annurev.soc.27.1.415 ↗
  48. Sivic, J. (2009). Efficient visual search of videos cast as text retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(4), 591–605. https://doi.org/10.1109/TPAMI.2008.111 ↗
  49. Rajaraman, A., & Ullman, J. D. (2011). Data mining. In Mining of Massive Datasets (pp. 1–17). find
  50. Mikolov, T., et al. (2013). Efficient estimation of word representations in vector space. In International Conference on Learning Representations (ICLR2013). https://doi.org/10.48550/arXiv.1301.3781 ↗
  51. Golbeck, J., Robles, C., & Turner, K. (2011). Predicting personality with social media. In CHI’11 Extended Abstracts on Human Factors in Computing Systems (pp. 253–262). https://doi.org/10.1145/1979742.1979614 ↗
  52. NERIS Analytics Limited. (2011-2023). Personality types. Retrieved from https://www.16personalities.com/personality-types ↗
  53. Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018). BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805v2. https://doi.org/10.48550/arXiv.1810.04805 ↗
  54. Antoun, W., Baly, F., & Hajj, H. (2020). AraBERT: Transformer-based model for Arabic language understanding. In LREC 2020 Workshop Language Resources and Evaluation Conference (pp. 11–16). https://doi.org/10.48550/arXiv.2003.00104 ↗ our card

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/dandash-2024-personality-analysis-social-media-users/