scholarly journals XLNet-Caps: Personality Classification from Textual Posts

Electronics ◽  
2021 ◽  
Vol 10 (11) ◽  
pp. 1360
Author(s):  
Ying Wang ◽  
Jiazhuang Zheng ◽  
Qing Li ◽  
Chenglong Wang ◽  
Hanyun Zhang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Social Networking Sites ◽  
Text Messages ◽  
Big Five Personality ◽  
Long Distance ◽  
Average Prediction Error ◽  
Text Information ◽  
Personality Recognition ◽  
Personality Features ◽  
Personality Classification

Personality characteristics represent the behavioral characteristics of a class of people. Social networking sites have a multitude of users, and the text messages generated by them convey a person’s feelings, thoughts, and emotions at a particular time. These social texts indeed record the long-term psychological activities of users, which can be used for research on personality recognition. However, most of the existing deep learning models for multi-label text classification consider long-distance semantics or sequential semantics, but problems such as non-continuous semantics are rarely studied. This paper proposed a deep learning framework that combined XLNet and the capsule network for personality classification (XLNet-Caps) from textual posts. Our personality classification was based on the Big Five personality theory and used the text information generated by the same user at different times. First, we used the XLNet model to extract the emotional features from the text information at each time point, and then, the extracted features were passed through the capsule network to extract the personality features further. Experimental results showed that our model can effectively classify personality and achieve the lowest average prediction error.

scholarly journals Encoding Text Information with Graph Convolutional Networks for Personality Recognition

2020 ◽  
Vol 10 (12) ◽  
pp. 4081
Author(s):  
Zhe Wang ◽  
Chun-Hua Wu ◽  
Qing-Biao Li ◽  
Bo Yan ◽  
Kang-Feng Zheng
Keyword(s):  
Personality Traits ◽  
Social Engineering ◽  
Big Five Personality ◽  
Convolutional Network ◽  
Convolutional Networks ◽  
Wide Range ◽  
Benchmark Datasets ◽  
Text Information ◽  
Class Labels ◽  
Personality Recognition

Personality recognition is a classic and important problem in social engineering. Due to the small number and particularity of personality recognition databases, only limited research has explored convolutional neural networks for this task. In this paper, we explore the use of graph convolutional network techniques for inferring a user’s personality traits from their Facebook status updates or essay information. Since the basic five personality traits (such as openness) and their aspects (such as status information) are related to a wide range of text features, this work takes the Big Five personality model as the core of the study. We construct a single user personality graph for the corpus based on user-document relations, document-word relations, and word co-occurrence and then learn the personality graph convolutional networks (personality GCN) for the user. The parameters or the inputs of our personality GCN are initialized with a one-hot representation for users, words and documents; then, under the supervision of users and documents with known class labels, it jointly learns the embeddings for users, words, and documents. We used feature information sharing to incorporate the correlation between the five personality traits into personality recognition to perfect the personality GCN. Our experimental results on two public and authoritative benchmark datasets show that the general personality GCN without any external word embeddings or knowledge is superior to the state-of-the-art methods for personality recognition. The personality GCN method is efficient on small datasets, and the average F1-score and accuracy of personality recognition are improved by up to approximately 3.6% and 2.4–2.57%, respectively.

scholarly journals A Single-Terminal Fault Location Method for HVDC Transmission Lines Based on a Hybrid Deep Network

Electronics ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 255
Author(s):  
Lei Wang ◽  
Yigang He ◽  
Lie Li
Keyword(s):  
Deep Learning ◽  
Transmission Lines ◽  
Fault Location ◽  
Short Term Memory ◽  
Engineering Application ◽  
Energy Operator ◽  
Sampling Frequency ◽  
Learning Technology ◽  
Long Distance ◽  
Hvdc Transmission

High voltage direct current (HVDC) transmission systems play an increasingly important role in long-distance power transmission. Realizing accurate and timely fault location of transmission lines is extremely important for the safe operation of power systems. With the development of modern data acquisition and deep learning technology, deep learning methods have the feasibility of engineering application in fault location. The traditional single-terminal traveling wave method is used for fault location in HVDC systems. However, many challenges exist when a high impedance fault occurs including high sampling frequency dependence and difficulty to determine wave velocity and identify wave heads. In order to resolve these problems, this work proposed a deep hybrid convolutional neural network (CNN) and long short-term memory (LSTM) network model for single-terminal fault location of an HVDC system containing mixed cables and overhead line segments. Simultaneously, a variational mode decomposition–Teager energy operator is used in feature engineering to improve the effect of model training. 2D-CNN was employed as a classifier to identify fault segments, and LSTM as a regressor integrated the fault segment information of the classifier to achieve precise fault location. The experimental results demonstrate that the proposed method has high accuracy of fault location, with the effects of fault types, noise, sampling frequency, and different HVDC topologies in consideration.

Addiction to Social Networking Sites and User Responses

2021 ◽  
Vol 52 (4) ◽  
pp. 65-91
Author(s):  
Hamed Qahri-Saremi ◽  
Isaac Vaghefi ◽  
Ofir Turel
Keyword(s):  
Social Networking ◽  
Personality Traits ◽  
Survey Data ◽  
Big Five ◽  
Social Networking Sites ◽  
Big Five Personality Traits ◽  
Social Networking Site ◽  
Big Five Personality ◽  
User Behaviors ◽  
Person Centered Approach

Prior studies have primarily used "variable-centered" perspectives to identify factors underlying user responses to social networking site (SNS) addiction, their predictors and outcomes. This paper extends this perspective by taking a person-centered approach to examine (1) the prototypical subpopulations (profiles) of users' extent of SNS addiction and responses to it, (2) how affiliations with these profiles can explain user behaviors toward SNS use, and (3) how personality traits can predict affiliations with these profiles. To this end, we propose a typological theory of SNS addiction and user responses to it via two empirical, personcentered studies. Study 1 draws on survey data from 188 SNS users to develop a typology of users based on the extent of their SNS addiction and their responses to it. It further examines the relations between affiliation with these profiles and users' SNS discontinuance intention, as a typical behavioral response to SNS addiction. Study 2 uses survey data from 284 SNS users to validate the user typology developed in Study 1 and investigate its relations to users' Big Five personality traits. Our findings shed light on a typology of five prototypical profiles of SNS users-cautious, regular, consonant, dissonant, and hooked-who differ in their extent of SNS addiction and their cognitive, emotional, and behavioral responses to it. Our findings also demonstrate how Big Five personality traits can predict user affiliations with these prototypical profiles.

Deep learning-based personality recognition from text posts of online social networks

2018 ◽  
Vol 48 (11) ◽  
pp. 4232-4246 ◽  
Author(s):  
Di Xue ◽  
Lifa Wu ◽  
Zheng Hong ◽  
Shize Guo ◽  
Liang Gao ◽  
...  
Keyword(s):  
Social Networks ◽  
Deep Learning ◽  
Online Social Networks ◽  
Personality Recognition

Predicting Personality Traits, Gender and Psychopath Behavior of Twitter Users

2014 ◽  
Vol 5 (2) ◽  
pp. 1-14 ◽  
Author(s):  
Hasan Ali AL Akram ◽  
Amjad Mahmood
Keyword(s):  
Social Networks ◽  
Personality Traits ◽  
Social Networking Sites ◽  
Information Exchange ◽  
Big Five Personality ◽  
Behavior Prediction ◽  
New Ideas ◽  
Twitter Users ◽  
Available Information ◽  
Insight Into

Social networking sites, such as Facebook and Twitter, are quickly becoming one of the most popular tools for social interaction and information exchange. Users of social networks reveal a lot about themselves in their public profiles, photos and status updates. While, social networks request users to create a truthful representation of themselves, they actually do so with a varying degree of accuracy. Depending on their privacy attitudes, the users may choose not to share details they find sensitive or tend to provide fake information. Contrary to a number of previous studies to predict the personality traits of the users of social networks primarily based on the users' profiles and other publically available information, this study provides an insight into the personality traits and psychopath behavior of twitter users by analyzing the tweets. The authors predict personality traits along the dimensions of “Big Five” personality model, gender and psychopath behavior of Twitter users. The paper discusses our data collection, gender, personality traits and psychopathic behavior prediction tool. It presents the analysis results of 327672 tweets of 345 users. The results show that there are more male users than the female users (70% male and 30% female). The results also show that majority of Twitter users are open to new ideas, are more agreeable and conscientious in nature but are less extravert. Out of 345 users, nine were indicating psychopath behavior and show less neuroticism. The authors also present a comparison of our personality traits' results with the results of two other similar studies.

Use of Social Networking Sites Among Shinas College of Technology Students in Oman

2012 ◽  
Vol 11 (01) ◽  
pp. 1250002 ◽  
Author(s):  
Salim Said Ali Al kindi ◽  
Saadat M. Alhashmi
Keyword(s):  
Focus Group ◽  
Social Networking ◽  
Social Networking Sites ◽  
Text Messages ◽  
Small Community ◽  
Technology Students ◽  
Frequent Use ◽  
College Of Technology ◽  
E Learning ◽  
Insufficient Time

Introduction: Social networking sites (SNSs) have become a popular method for students to share information and knowledge and to express emotions. They enable students to exchange video files, text messages, pictures and knowledge sharing. They provide an opportunity for students to improve social networking and learning processes, which promotes knowledge in society. Purposes: This paper intends to address the factors motivating students at colleges to use SNSs, to identify the factors that motivate them in using SNSs for educational purposes and to identify the most popular SNSs among students. Design/Methodology: The study uses a questionnaire in order to discover the reasons behind the use of SNSs by students at Shinas College of Technology (ShCT) in Oman. Findings: The study found that the major reasons for frequent use of SNSs are finding information and sharing news. The study also indicated that lack of experience as well as insufficient time and IT skills are effective factors of not using SNSs. Finally, the study discovered that Google Groups, Facebook and Yahoo! 360 are the most popular SNSs used by SHCT students. Research Limitation: The study was limited to ShCT students, which is considered a small community, and the focus group was relatively small. A larger focus group in a different environment may possibly yield different results. Additionally, the list of SNSs listed in the questionnaire was based on previous studies discussed in the literature review. Originality/value: This research will be valuable for those interested in the subject of social networks and e-learning. In this area, there is a dearth of research on reasons for student use of SNSs in Oman, giving this particular research great importance to understanding the way that students interact with SNSs.

Use of WhatsApp for Effective Delivery of Library and Information Services

2017 ◽  
Vol 37 (5) ◽  
pp. 360
Author(s):  
Mohd Shoaib Ansari ◽  
Aditya Tripathi
Keyword(s):  
Social Networking ◽  
Communication Technology ◽  
Social Networking Sites ◽  
Positive Attitude ◽  
Online Survey ◽  
Text Messages ◽  
Information Communication ◽  
Online Questionnaire ◽  
Virtual Reference ◽  
Effective Delivery

<div class="page" title="Page 1"><div class="layoutArea"><div class="column"><p><span>Information communication technology playing a major role in transmitting idea, thought and information between one to another. Social networking websites are a good example of communication network and it is a social structure that lets the user interact and work collaboratively with other users. WhatsApp is a free instant </span><span>messenger application that allows users to send text messages and multimedia files. In this paper, an online survey </span><span>was conducted to measure usability of WhatsApp for service delivery in the libraries and information centres. A random sample was selected from social networking sites from all over India and an online questionnaire was used to gather information from respondents. Findings indicated that respondents showed a positive attitude toward getting services over WhatsApp. Most of the respondents believe that use of WhatsApp can improve alert services (CAS, </span><span>virtual reference, notifications) and libraries can utilise their potential for providing better user services. </span></p></div></div></div>

Sign in / Sign up

Export Citation Format

Share Document