scholarly journals Semantic Approach for Big Five Personality Prediction on Twitter

2021 ◽  
Vol 5 (4) ◽  
pp. 680-687
Author(s):  
Ghina Dwi Salsabila ◽  
Erwin Budi Setiawan
Keyword(s):  
Big Five ◽  
Online Survey ◽  
Support Vector ◽  
Big Five Personality ◽  
Accuracy Score ◽  
Prediction System ◽  
Semantic Approach ◽  
Linguistic Feature ◽  
Personality Prediction ◽  
Twitter Users

Personality provides a deep insight of someone and has an important part in someone’s job performance. Predicting personality through social media has been studied on several research. The problem is how to improve the performance of personality prediction system. The purpose of this research is to predict personality on Twitter users and increase the performance of the personality prediction system. An online survey using Big Five Inventory (BFI) questionnaire has been distributed and gathered 295 Twitter users with 511,617 tweets data. In this research, we experiment on two different methods using Support Vector Machine (SVM), and the combination of SVM and BERT as the semantic approach. This research also implements Linguistic Inquiry Word Count (LIWC) as the linguistic feature for personality prediction system. The results showed that combination of these two methods achieve 79.35% accuracy score and with the implementation of LIWC can improve the accuracy score up to 80.07%. Overall, these results showed that the combination of SVM and BERT as the semantic approach with the implementation of LIWC is recommended to gain a better performance for the personality prediction system.  

scholarly journals Big Five Personality Prediction from Social Media Data using Machine Learning Techniques

2020 ◽  
Vol 9 (4) ◽  
pp. 2412-2417
Keyword(s):  
Machine Learning ◽  
Big Five ◽  
Machine Learning Techniques ◽  
Big Five Personality ◽  
Learning Techniques ◽  
Machine Learning Model ◽  
Personality Prediction ◽  
Twitter Users ◽  
Bayes Algorithm ◽  
Media Data

Personality has been important for a number of types of cooperation; it has useful in predicting job achievement, expert and emotional relationship achievement, and even tendency towards a variety of interfaces. To accurately examine the characters of users, a personality test must be carried out. In numerous areas of online life it is usually impractical to use character research. . We used SVM classification, Random Forest algorithm, Naïve Bayes Algorithm and Logistic regression to comparatively predict the user’s personality accurately. The main goal of the paper is to evaluate the machine learning models using the four parameters- accuracy, precision, recall, f1 score and basing upon these parameters the best machine learning model will be used to classify the big five personality traits of the twitter users.

scholarly journals Big five personality prediction based in Indonesian tweets using machine learning methods

2022 ◽  
Vol 12 (2) ◽  
pp. 1973
Author(s):  
Warih Maharani ◽  
Veronikha Effendy
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Big Five ◽  
Machine Learning Techniques ◽  
Social Characteristics ◽  
Support Vector ◽  
Big Five Personality ◽  
Semantic Features ◽  
Learning Techniques ◽  
Personality Prediction

<span lang="EN-US">The popularity of social media has drawn the attention of researchers who have conducted cross-disciplinary studies examining the relationship between personality traits and behavior on social media. Most current work focuses on personality prediction analysis of English texts, but Indonesian has received scant attention. Therefore, this research aims to predict user’s personalities based on Indonesian text from social media using machine learning techniques. This paper evaluates several machine learning techniques, including <a name="_Hlk87278444"></a>naive Bayes (NB), K-nearest neighbors (KNN), and support vector machine (SVM), based on semantic features including emotion, sentiment, and publicly available Twitter profile. We predict the personality based on the big five personality model, the most appropriate model for predicting user personality in social media. We examine the relationships between the semantic features and the Big Five personality dimensions. The experimental results indicate that the Big Five personality exhibit distinct emotional, sentimental, and social characteristics and that SVM outperformed NB and KNN for Indonesian. In addition, we observe several terms in Indonesian that specifically refer to each personality type, each of which has distinct emotional, sentimental, and social features.</span>

Gender Differences in Relationship Between Resilience and Big Five Personality Traits in Japanese Adolescents

2017 ◽  
Vol 121 (5) ◽  
pp. 920-931 ◽  
Author(s):  
Shuhei Iimura ◽  
Kanako Taku
Keyword(s):  
Gender Differences ◽  
Personality Traits ◽  
Big Five ◽  
Online Survey ◽  
Big Five Personality Traits ◽  
Big Five Personality ◽  
School Students ◽  
Five Dimensions ◽  
Japanese Adolescents ◽  
Age Range

Prior work has indicated that female adolescents mature more quickly than males with regard to the various personality dimensions. From the developmental perspectives, this study aimed to explore gender differences in the relationships between resilience and the Big Five personality traits in Japanese adolescents. Middle school students ( N = 310, 155 females, age range = 14–15 years) participated in an online survey. The results demonstrated that females had higher Conscientiousness than males. Stepwise regression analyses indicated that Neuroticism was the most influential predictor of resilience in females, whereas Extraversion was the most important predictor in males. Multigroup path analysis demonstrated that the effect of Neuroticism on resilience was greater for females; however, the effects of all other variables did not differ across genders. Considering gender differences is important to understand the relationship between resilience and the Big Five dimensions among adolescents.

Exploring Valued Personality Traits in Practicing Veterinarians

2021 ◽  
pp. e20210051
Author(s):  
Andrea J. Kunze ◽  
Christopher Seals
Keyword(s):  
Veterinary Medicine ◽  
Personality Traits ◽  
Big Five ◽  
Online Survey ◽  
Age Groups ◽  
Small Animal ◽  
Emotional Stability ◽  
Big Five Personality ◽  
Pet Owners ◽  
Medicine Community

We examined differences in valued Big Five personality traits of small animal veterinarians between members and nonmembers of the veterinary medicine community. Between fall 2019 and spring 2020, data were collected from an online survey sent to eligible persons across a US midwestern state. Eligible persons included veterinary office clients (i.e., pet owners) and persons practicing/training in veterinary medicine. Participants completed demographic questions and 10 Likert scale items about which Big Five personality characteristics they prefer in a veterinarian. Descriptive data were determined and checked for assumptions of linearity and normality. Data for the primary analyses were analyzed using Spearman’s correlations and Kruskal–Wallis H tests. Participants who were members of the veterinary community of practice valued the characteristic openness more than clients but valued emotional stability less than clients. Moreover, tests revealed that young adults (aged 18–24) valued extraversion more than all other age groups but least valued agreeableness. Last, participants aged 55 and older valued agreeableness and emotional stability more than the 18–44 age groups. Findings indicate individuals from different membership and age groups have varying preferences in what personality traits they expect in a veterinarian. Clients care more about their veterinarian being able to handle adversity. Older adults want their veterinarian to be trusting and creative. These findings encourage veterinary medical education to spotlight the development of skills congruent with these desired personality traits. Gaining such skills will be useful for veterinarians who seek to grow or build lasting relationships with clientele and colleagues.

Moderation effect of pleasure seeking and loss aversion in the relationship between personality traits and risky investment intention

Kybernetes ◽  
2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Selim Aren ◽  
Hatice Nayman Hamamci ◽  
Safvan Özcan
Keyword(s):  
Personality Traits ◽  
Big Five ◽  
Loss Aversion ◽  
Online Survey ◽  
Big Five Personality Traits ◽  
Big Five Personality ◽  
Moderator Effect ◽  
Content Type ◽  
Risky Investment ◽  
Investment Intentions

Purpose The aim of this study, the moderating effect of pleasure-seeking and loss aversion, was investigated in relation to the big five personality traits with regard to risky investment intentions. Design/methodology/approach In the study, the data was obtained between January and November 2019 via an online survey with convenience sampling. The total number of subjects is 886. The authors used IBM SPSS Statistics for analysis. Exploratory factor analysis, correlation analysis, regression analysis and discriminant analysis were performed. Findings Significant relationships were found between five personality traits and risky investment intentions. In these relationships, the moderator effect of pleasure-seeking for extraversion, conscientiousness and neuroticism personality traits was also determined. Besides, investment preferences for choosing “unknown and new investment” against “known and experienced investment”, which is a typical feature of the balloon periods, were modeled with big five personality traits and motivation variables (pleasure-seeking and loss aversion) and the equation was formed. As a result, high accuracy classification success was obtained. Originality/value The study is unique owing to its findings. In addition, general risk aversion and risky investment intention were investigated simultaneously to explain the different findings in the literature regarding the attitude of big five personality traits to risk and personality traits that show consistent approach were identified.

scholarly journals COVID-19 Pandemic and Personality: Agreeable People Are More Stressed by the Feeling of Missing

2021 ◽  
Vol 18 (20) ◽  
pp. 10759
Author(s):  
Stephan Getzmann ◽  
Jan Digutsch ◽  
Thomas Kleinsorge
Keyword(s):  
Mental Health ◽  
Personality Traits ◽  
Perceived Stress ◽  
Big Five ◽  
Online Survey ◽  
Well Being ◽  
Big Five Personality Traits ◽  
Big Five Personality ◽  
Negative Effects ◽  
Related Individual

The COVID-19 pandemic and the measures taken to contain it have substantial consequences for many people, resulting in negative effects on individual well-being and mental health. In the current study, we examined whether individual changes in perceived stress relative to pre-pandemic levels depended on differences in behavior, appraisal, and experience of pandemic-related constraints. In addition, we tested whether this potential relationship was moderated by personality traits. We conducted an online survey during the end of the first lockdown in Germany in spring 2020, and assessed pandemic-related individual consequences as well as perceived stress. These data were related to the big five personality traits and to ratings of perceived stress obtained from the same participants in a study conducted before the outbreak of the pandemic, using the same standardized stress questionnaires. There was no overall increase, but a large interindividual variety in perceived stress relative to pre-pandemic levels. Increased stress was associated especially with strong feelings of missing. This relationship was moderated by agreeableness, with more agreeable people showing a higher association of the feeling of missing and the increase of perceived stress. In addition, openness and conscientiousness were positively correlated with an increase in stress. The results highlight the importance of considering personality and individual appraisals when examining the consequences of the COVID-19 pandemic on perceived stress and well-being.

scholarly journals The Swedish Version of the Multidimensional Inventory for Religious/Spiritual Well-Being: First Results From Swedish Students

2021 ◽  
Vol 12 ◽  
Author(s):  
Magdalena Wenzl ◽  
Jürgen Fuchshuber ◽  
Nikita Podolin-Danner ◽  
Giorgia Silani ◽  
Human-Friedrich Unterrainer
Keyword(s):  
Mental Health ◽  
Big Five ◽  
Sense Of Coherence ◽  
Online Survey ◽  
Well Being ◽  
Dimensional Structure ◽  
Personality Factors ◽  
Big Five Personality ◽  
Swedish Version ◽  
Spiritual Well Being

Background: Studies investigating the relationship between religiosity/spirituality and mental health have suggested both positive and negative associations, highlighting the importance of multifaceted assessment of these rather broad constructs. The present study aims at contributing to this field of research by providing a validated Swedish version of the Multidimensional Inventory for Religious/Spiritual Well-Being (MI-RSWB-S) and further examining how this instrument relates to Big Five personality factors, Sense of Coherence (SOC), and religiosity.Methods: Data were collected from a total of 1,011 Swedish students (747 females; age range 18–40) via completion of an online survey, including a new Swedish Version of the MI-RSWB-S, the Ten Item Personality Inventory (TIPI), the Sense of Coherence Scale (SOC-13), and the Centrality of Religiosity Scale (CRS-5).Results: Results revealed adequate estimates of internal consistency and substantial evidence for the postulated six-dimensional structure. However, confirmatory factor analysis yielded poor fit indices, resulting in the development and validation of a revised measure of Religious/Spiritual Well-Being (RSWB), comprising the subscales General Religiosity and Connectedness. Most of the MI-RSWB-S dimensions were positively correlated with the personality domains Extraversion, Openness to Experience, Conscientiousness, and Agreeableness and negatively related to Neuroticism. SOC was positively linked to Hope Immanent, Forgiveness, Hope Transcendent, and Experiences of Sense of Meaning, whereas CRS exhibited positive correlations with all MI-RSWB-S subscales except Hope Transcendent.Conclusion: The findings of the current study support the validity and reliability of the Swedish adoption of the MI-RSWB and confirm previously reported associations with the Big Five personality traits, SOC, and CRS. More in general, our results underline the putative substantial link between RSWB dimensions and mental health. Further research especially in clinical surroundings as well as by employing more representative samples is now warranted.

scholarly journals Appreciation (Including Gratitude) and Affective Well-Being: Appreciation Predicts Positive and Negative Affect Above the Big Five Personality Factors and Demographics

SAGE Open ◽  
2018 ◽  
Vol 8 (4) ◽  
pp. 215824401881862 ◽  
Author(s):  
N. S. Fagley
Keyword(s):  
Negative Affect ◽  
Big Five ◽  
Online Survey ◽  
Well Being ◽  
Future Research ◽  
Personality Factors ◽  
Big Five Personality ◽  
Positive And Negative Affect ◽  
Big Five Traits ◽  
Big Five Personality Factors

This study investigated the relation between appreciation and positive and negative affect, controlling for gender, age, ethnicity, and Big Five personality factors. Appreciation consists of several aspects, including a focus on what one has (“have” focus), awe, gratitude, and interpersonal appreciation. Undergraduates ( N = 236) completed an online survey containing the Appreciation Scale, Positive and Negative Affect Scale (PANAS), and Big Five Inventory (BFI). The Big Five traits accounted for 38% and 43% of the variance in positive and negative affect, respectively, beyond demographics. Appreciation accounted for 9% ( p < .001) and 4.6% ( p < .05) of the variance in positive and negative affect, respectively, beyond demographics and the Big Five. The “have” focus aspect of appreciation, which represents noticing, focusing on, and valuing what one has, accounted for significant unique variance in both positive and negative affect. Gratitude did not. Future research is needed to determine how broadly these results generalize.

The REIm-13

2019 ◽  
Vol 35 (4) ◽  
pp. 451-458
Author(s):  
Clare E. McGuiness ◽  
Ian Zajac ◽  
Carlene Wilson ◽  
Deborah Turnbull
Keyword(s):  
Big Five ◽  
Online Survey ◽  
Short Form ◽  
Community Sample ◽  
Negative Relationship ◽  
Reliability And Validity ◽  
Big Five Personality ◽  
Thinking Style ◽  
Structure Reliability ◽  
Test Retest Reliability

Abstract. The Rational-Experiential Multimodal Inventory (REIm) is a recent tool showing promise in the measurement of self-reported thinking style – preference for rational or experiential processing – and offers three-faceted measurement of the latter. We present the first short form of the measure, the REIm-13, and test its factor structure, reliability, and validity in a large community sample. Participants were N = 920 Australian adults (502 females) who completed an online survey ( N = 510 of whom participated in a follow-up survey). In addition to the REIm, participants completed a Big Five personality measure. The internal consistency of the REIm-13 was acceptable given the limited number of items (.52–.68). Furthermore, test-retest reliability was high (ρ = .64–.74) for the theorized four-factor and two-factor solutions. Construct validity was established by examining the relationship between short-form and full REIm factors (ρ = .65–.71), and the validity of composite scoring was confirmed against factor scoring. Relationship with age (a slight negative relationship to both main scales), gender (females reporting higher Experientiality, males higher Rationality), and Big Five variables largely followed previous findings, demonstrating concurrent validity. The study demonstrates that the REIm-13 provides sound measurement of thinking style.

Sign in / Sign up

Export Citation Format

Share Document