Automatic Personality Evaluation from Transliterations of YouTube Vlogs Using Classical and State of the art Word Embeddings

López-Pabón, Felipe Orlando; Orozco-Arroyave, Juan Rafael

doi:10.15446/ing.investig.93803

Cited by 7 publications

(4 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While for Youtube dataset, this research achieves an average f1 score 0,741. Compared to previous results that used Youtube dataset also, this result provided a good result and was better than the research done by [15] that resulted best f1 score 0,612. One of the reasons for the result is this research modified the dataset to minimize imbalance class with the data augmentation method.…”

Section: Discussioncontrasting

confidence: 55%

See 1 more Smart Citation

Personality Identification from Social Media Using Ensemble Bert and Roberta

Tsani,

Suhartono

2023

IJCAI

View full text Add to dashboard Cite

Social media growth was fast because many people used it to express their feelings, share information, and interact with others. With the growth of social media, many researchers are interested in using social media data to conduct research about personality identification. The identification result can be used as a parameter to screen candidate attitudes in the company's recruitment process. Some approaches were used for research about personality; one of the most popular is the Big Five Personality Model. In this research, an ensemble model between BERT and RoBERTa was introduced for personality prediction from the Twitter and Youtube datasets. The data augmentation method also introduces to handling the imbalance class for each dataset. Pre-trained model BERT and RoBERTa was used as the feature extraction method and modeling process. To predict each trait in the Big Five Personality, the voting ensemble from BERT and RoBERTa achieved an average f1 score 0,730 for Twitter dataset and 0,741 for Youtube dataset. Using the proposed model, we conclude that data augmentation can increase average performance compared to the model without data augmentation process.Povzetek: Članek uvaja model združevanja siestemov BERT in RoBERTa za napovedovanje osebnosti iz podatkov Twitterja (X) in Youtube, z izboljšanjem s pomočjo podatkovne augmentacije.

show abstract

Section: Discussioncontrasting

confidence: 55%

“…Decision tree and SVM algorithm were used and produced better results over baseline average performance. Another research using Youtube dataset was also conducted by [15]. This research uses Youtube translations only to create a model using Word2Vec, GloVe, and BERT as feature extraction methods then uses SVM and SVR for classification.…”

Section: Related Workmentioning

confidence: 99%

Personality Identification from Social Media Using Ensemble Bert and Roberta

Tsani,

Suhartono

2023

IJCAI

View full text Add to dashboard Cite

show abstract

“…Jiang, et al [8] presented a novel approach to automatic personality detection using RoBERT and attentive neural networks for the Big Five. Furthermore, Padon et al [9] adopted three pre-trained language models -Word2Vec, GloVe, and BERT to classify Big Five personality traits. Demerdash et al [10] used three pre-trained models including Elmo, ULMFiT, and BERT to extract features and achieved the State-of-the-Art results on myPersonality dataset.…”

Section: Text-based Big Five Personality Predictionmentioning

confidence: 99%

Big five personality prediction based on pre-training language model and sentiment knowledge base

Lin,

2023

Sixth International Conference on Computer Information Science and Application Technology (CISAT 2023)

View full text Add to dashboard Cite

Machine learning-based personality prediction methods have become the mainstream prediction method. But existing Big Five personality prediction methods based on user-generated text rely too much on pre-trained language models to ignore the sentiment information. To tackle these issues, we propose a novel Big Five personality prediction method based on pre-trained language models and SenticNet6, which is a new sentiment knowledge base. The correlation analysis and ablation experiment shows that SenticNet6 can be used for Big Five personality prediction tasks. The experiment results indicate that our proposed method improves the state-of-art results for each Big Five personality trait by 9.89%, 9.39%, 2.99%, 3.01%, and 4.28% on Essays dataset, respectively.

show abstract

“…The work of Roussmann et al [6] confirms that personality is related to the situations people encounter and their interpretations of them, so it is possible to predict how they will act in their daily lives through the OCEAN personality model. Lopez et al [7], who attempted to automate personality assessments from transliterations of YouTube vlogs using classic and state-of-the-art word embeddings, argue that personality trait studies based on language patterns also need to take into account the knowledge of psychologists and psycholinguists to collect and label data. Holman et al [8] researched the interaction between the Big-5 personality traits and work characteristics, and it was found that the work characteristics had an impact on the personality traits.…”

Section: Introductionmentioning

confidence: 99%

User OCEAN Personality Model Construction Method Using a BP Neural Network

Qin¹,

Liu

et al. 2022

Electronics

View full text Add to dashboard Cite

In the era of big data, the Internet is enmeshed in people’s lives and brings conveniences to their production and lives. The analysis of user preferences and behavioral predictions of user data can provide references for optimizing information structure and improving service accuracy. According to the present research, user’s behavior on social networking sites has a great correlation with their personality, and the five characteristics of the OCEAN (Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism) personality model can cover all aspects of a user’s personality. It is important in identifying a user’s OCEAN personality model to analyze their digital footprints left on social networking sites and to extract the rules of users’ behavior, and then to make predictions about user behavior. In this paper, the Latent Dirichlet Allocation (LDA) topic model is first used to extract the user’s text features. Second, the extracted features are used as sample input for a BP neural network. The results of the user’s OCEAN personality model obtained by a questionnaire are used as sample output for a BP neural network. Finally, the neural network is trained. A mapping model between the probability of the user’s text topic and their OCEAN personality model is established to predict the latter. The results show that the present approach improves the efficiency and accuracy of such a prediction.

show abstract

Automatic Personality Evaluation from Transliterations of YouTube Vlogs Using Classical and State of the art Word Embeddings

Cited by 7 publications

References 41 publications

Personality Identification from Social Media Using Ensemble Bert and Roberta

Personality Identification from Social Media Using Ensemble Bert and Roberta

Big five personality prediction based on pre-training language model and sentiment knowledge base

User OCEAN Personality Model Construction Method Using a BP Neural Network

Contact Info

Product

Resources

About