Modelling personality prediction from user's posting on social media

Author(s):  
Derwin Suhartono
Author(s):  
Hetal Vora ◽  
Mamta Bhamare ◽  
Dr. K. Ashok Kumar ◽  

Author(s):  
Lei Zhang ◽  
Liang Zhao ◽  
Xuchao Zhang ◽  
Wenmo Kong ◽  
Zitong Sheng ◽  
...  

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Hans Christian ◽  
Derwin Suhartono ◽  
Andry Chowanda ◽  
Kamal Z. Zamli

AbstractThe ever-increasing social media users has dramatically contributed to significant growth as far as the volume of online information is concerned. Often, the contents that these users put in social media can give valuable insights on their personalities (e.g., in terms of predicting job satisfaction, specific preferences, as well as the success of professional and romantic relationship) and getting it without the hassle of taking formal personality test. Termed personality prediction, the process involves extracting the digital content into features and mapping it according to a personality model. Owing to its simplicity and proven capability, a well-known personality model, called the big five personality traits, has often been adopted in the literature as the de facto standard for personality assessment. To date, there are many algorithms that can be used to extract embedded contextualized word from textual data for personality prediction system; some of them are based on ensembled model and deep learning. Although useful, existing algorithms such as RNN and LSTM suffers from the following limitations. Firstly, these algorithms take a long time to train the model owing to its sequential inputs. Secondly, these algorithms also lack the ability to capture the true (semantic) meaning of words; therefore, the context is slightly lost. To address these aforementioned limitations, this paper introduces a new prediction using multi model deep learning architecture combined with multiple pre-trained language model such as BERT, RoBERTa, and XLNet as features extraction method on social media data sources. Finally, the system takes the decision based on model averaging to make prediction. Unlike earlier work which adopts a single social media data with open and close vocabulary extraction method, the proposed work uses multiple social media data sources namely Facebook and Twitter and produce a predictive model for each trait using bidirectional context feature combine with extraction method. Our experience with the proposed work has been encouraging as it has outperformed similar existing works in the literature. More precisely, our results achieve a maximum accuracy of 86.2% and 0.912 f1 measure score on the Facebook dataset; 88.5% accuracy and 0.882 f1 measure score on the Twitter dataset.


Author(s):  
Gokalp Mavis ◽  
Ismail Hakki Toroslu ◽  
Pinar Karagoz

According to the psychology literature, there is a strong correlation between the personality traits and the linguistic behavior of people. Due to increase in computer based communication, individuals express their personalities in written forms on social media. Hence, social media became a convenient resource to analyze the relationship between the personality traits and the lingusitic behaviour. Although there is a vast amount of studies on social media, only a small number of them focus on personality prediction. In this work, we aim to model the relationship between the social media messages of individuals and Big Five Personality Traits as a supervised learning problem. We use Twitter posts and user statistics for analysis. We investigated various approaches for user profile representation, explored several supervised learning techniques, and presented comparative analysis results. Our results confirm the findings of psychology literature, and we show that computational analysis of tweets using supervised learning methods can be used to determine the personality of individuals.


2020 ◽  
pp. 1-10
Author(s):  
Jinghua Zhao ◽  
Jie Lin ◽  
Shuang Liang ◽  
Mengjiao Wang

The paper first analyzes the correlation between text sentiment values and personality traits, proves that text sentiment can have a good support effect on user personality prediction, then on this basis, a method based on CNN-LSTM is proposed, which can be used to deeply analyze the sentiment analysis capability of the model, hoping to improve the precision of sentiment classification and lay a solid foundation for the next experiment. This experiment proves that the CNN-LSTM constructed in this paper can better predict the emotional tendency of the short text of microblog, has good generalization ability, and has higher precision than other methods.


2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Yuting Jiang ◽  
Shengli Deng ◽  
Hongxiu Li ◽  
Yong Liu

PurposeThe purposes of this paper are to (1) explore how personality traits pertaining to the dominance influence steadiness compliance model manifest themselves in terms of user interaction behavior on social media and (2) examine whether social interaction data on social media platforms can predict user personality.Design/methodology/approachSocial interaction data was collected from 198 users of Sina Weibo, a popular social media platform in China. Their personality traits were also measured via questionnaire. Machine learning techniques were applied to predict the personality traits based on the social interaction data.FindingsThe results demonstrated that the proposed classifiers had high prediction accuracy, indicating that our approach is reliable and can be used with social interaction data on social media platforms to predict user personality. “Reposting,” “being reposted,” “commenting” and “being commented on” were found to be the key interaction features that reflected Weibo users' personalities, whereas “liking” was not found to be a key feature.Originality/valueThe findings of this study are expected to enrich personality prediction research based on social media data and to provide insights into the potential of employing social media data for the purpose of personality prediction in the context of the Weibo social media platform in China.


The undeniable power that various e-commerce and streaming websites exert on their users’ in terms of what they buy and what they watch is unquestionable, so the creation of better targeted advertisements and recommender systems is the need of the hour. Prediction of a person’s personality can be the key for the achievement of these goals. A novel way to understand the various facets of a person’s personality is by analyzing their MBTI (Myers–Briggs Type Indicator). This paper aims at classifying a user into any one of the sixteen personality types, defined by MBTI, through the use of natural language processing (NLP) and support vector machine (SVM) which was implemented on the MBTI dataset. Since the original dataset is unevenly distributed, SVM has been applied to the original dataset and an under sampled version of the MBTI dataset. The highest accuracy rate of 78.52% for the traits (thinking/feeling) was achieved in the original dataset whereas for the under sampled dataset it was 60.2% for the traits (judging/perceiving).


Sign in / Sign up

Export Citation Format

Share Document