Cross-platform personality exploration system for online social networks: Facebook vs. Twitter

Tareaf, Raad Bin; Berger, Philipp; Hennig, Patrick; Meinel, Christoph

doi:10.3233/web-200427

Cited by 6 publications

(2 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first dataset called the MyPersonality dataset, which consists of 250 users with a total of 9917 statuses. This dataset is collected through a Facebook app in 2007, allowing users to participate in psychological research by filling in the personality questionnaire [7]. The second dataset is an expanded dataset from previous research done by [27], which is a manually collected twitter data in Bahasa Indonesia.…”

Section: Datamentioning

confidence: 99%

Text based personality prediction from multiple social media data sources using pre-trained language model and model averaging

et al. 2021

View full text Add to dashboard Cite

The 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.

show abstract

Section: Datamentioning

confidence: 99%

Text based personality prediction from multiple social media data sources using pre-trained language model and model averaging

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The theory of social presentation meant that people desired to influence others during the social media-assisted communication. They might either wish to obtain rewards or establish their own social identities or statuses (Bin Tareaf et al, 2020), which could be realized through self-disclosure. Self-disclosure acted as an important step for communicators to establish mutually trustable interpersonal relationships.…”

Section: Resultsmentioning

confidence: 99%

Bibliometric analyses of social media for educational purposes over four decades

Sukjairungwattana

2023

Front. Psychol.

View full text Add to dashboard Cite

The unexpected outbreak of COVID-19 pandemic has led students to frequently use social media to receive education, which brought about both positive and negative learning outcomes (Oliveira et al., 2022). To address the issue of integrating social media into education, this study conducted both quantitative and qualitative studies using VOSviewer and CitNetExplorer. The qualitative study through CitNetExplorer, involving 1780 publications, concluded that while social media might have gained popularity in education based on the classic theoretical framework of the zone of proximal development, there might be many challenges such as teacher resistance, data privacy, costs, and ethical and social issues. Besides, this study conducted bibliometric analyses using VOSviewer (N = 1841) to identify the top cited authors, organizations, documents, references, sources, countries, and keywords with high occurrences based on the citation networks. In the future, researchers could enhance the studies on how to guide students and teachers to properly integrate social media into education.

show abstract

Predicting human behavior from social media using mRMR with COA

Kamalesh

Bharathi²

2022

Int J Syst Assur Eng Manag

View full text Add to dashboard Cite

Cross-platform personality exploration system for online social networks: Facebook vs. Twitter

Cited by 6 publications

References 20 publications

Text based personality prediction from multiple social media data sources using pre-trained language model and model averaging

Text based personality prediction from multiple social media data sources using pre-trained language model and model averaging

Bibliometric analyses of social media for educational purposes over four decades

Predicting human behavior from social media using mRMR with COA

Contact Info

Product

Resources

About