Psychological Profiles Prediction Using Online Social Network Behavior Data

2019 ◽  
pp. 75-87
Author(s):  
Nan Zhao ◽  
Tingshao Zhu
Keyword(s):  
Machine Learning ◽  
Social Network ◽  
Individual Differences ◽  
Predictive Accuracy ◽  
Daily Life ◽  
Online Social Network ◽  
Online Behavior ◽  
Huge Amount ◽  
Psychological Profiles ◽  
Data Source

As today's online social network (OSN) has become a part of our daily life, the huge amount of OSN behavior data could be a new data source to detect and understand individual differences, especially on mental aspects. Based on the findings revealing the relationships between personality and online behavior records, the authors tried to extract relevant features from both OSN usage behaviors and OSN textual posts, and trained models by machine learning methods to predict the OSN user's personality. The results showed fairly good predictive accuracy in Chinese OSN. The authors also reviewed the same kind of studies in more pervasive OSNs, focusing on what behavior data are used in predicting psychological profiles and how to use them effectively. It is foreseeable that more types of OSN data could be utilized in recognizing more psychological indices, and the predictive accuracy would be further improved. Meanwhile, the model-predicted psychological profiles are becoming an option of measurements in psychological studies, when the classical methods are not applicable.

Filtering Dirty Words in Online Social Network by Applying Automated Filtering System

2014 ◽  
Vol 573 ◽  
pp. 560-564
Author(s):  
P. Kumari Bala ◽  
D. Jemi Florinabel ◽  
S. Sivasakthi
Keyword(s):  
Machine Learning ◽  
Social Network ◽  
Online Social Networks ◽  
Text Categorization ◽  
Online Social Network ◽  
Project Work ◽  
Rule Based ◽  
Short Text ◽  
Filter Algorithms ◽  
Content Based Filtering

The aim of the project work is automatically to filter the dirty words from other users without displaying to the profile owner. In Online Social Network may have possibilities of posting some dirty messages so it need to filter without displaying to owner. It has achieved by using Rule based Filtering System. The Rule Based Filtering System allows users customize to filter the noisy or dirty words by applying some filtering Criteria. It exploits Machine Learning (ML). Machine Learning is a text categorization techniques to specify some categories for assign the short text dirty words based on their content. The content-based filtering on messages posted on user space has specified the additional challenges to be given the short length of these messages. Online social networks not only make it easier for users to share their opinions with each other, but also serve as a platform for developing filter algorithms.

scholarly journals Bots Recognition in Social Networks Using the Random Forest Algorithm

2019 ◽  
pp. 24-41
Author(s):  
M. G. Khachatrian ◽  
P. G. Klyucharev
Keyword(s):  
Machine Learning ◽  
Social Networks ◽  
Social Network ◽  
Random Forest ◽  
Online Social Networks ◽  
Learning Algorithm ◽  
Online Social Network ◽  
Machine Learning Algorithms ◽  
Random Forest Algorithm ◽  
Twitter Account

Online social networks are of essence, as a tool for communication, for millions of people in their real world. However, online social networks also serve an arena of information war. One tool for infowar is bots, which are thought of as software designed to simulate the real user’s behaviour in online social networks.The paper objective is to develop a model for recognition of bots in online social networks. To develop this model, a machine-learning algorithm “Random Forest” was used. Since implementation of machine-learning algorithms requires the maximum data amount, the Twitter online social network was used to solve the problem of bot recognition. This online social network is regularly used in many studies on the recognition of bots.For learning and testing the Random Forest algorithm, a Twitter account dataset was used, which involved above 3,000 users and over 6,000 bots. While learning and testing the Random Forest algorithm, the optimal hyper-parameters of the algorithm were determined at which the highest value of the F1 metric was reached. As a programming language that allowed the above actions to be implemented, was chosen Python, which is frequently used in solving problems related to machine learning.To compare the developed model with the other authors’ models, testing was based on the two Twitter account datasets, which involved as many as half of bots and half of real users. As a result of testing on these datasets, F1-metrics of 0.973 and 0.923 were obtained. The obtained F1-metric values  are quite high as compared with the papers of other authors.As a result, in this paper a model of high accuracy rates was obtained that can recognize bots in the Twitter online social network.

scholarly journals A Machine Learning-based Online Social Network Analysis for 360-degree User Profiling

2019 ◽  
Vol 9 (2S2) ◽  
pp. 992-998
Keyword(s):  
Machine Learning ◽  
Social Network ◽  
Social Networking Sites ◽  
Online Social Network ◽  
User Profiling ◽  
Machine Learning Technique ◽  
The People ◽  
Learning Technique ◽  
The Government ◽  
Personal Interests

This paper aims to analyse the online social network for reconnaissance of people for finding their potentiality. The work considers one of the famous social networking sites, Twitter, where people express their thoughts and ideas, through which the people in the site knowingly or unknowingly reveal the information about themselves such as personal interests, likes and dislikes. The Machine Learning technique facilitates the work to mine the tweet data of a person to get his/her 360-degree profiling. This profiling is helpful to identify the personality type of a person, which is essential for the Government to identify the people involved in spreading the fake news in Twitter.

scholarly journals SENTIMENT ANALYSIS OF ENGLISH TWEETS USING BIGRAM COLLOCATION

2021 ◽  
pp. 220-227
Author(s):  
Sumaya Ishrat Moyeen ◽  
Md. Sadiqur Rahman Mabud ◽  
Zannatun Nayem ◽  
Md. Al Mamun
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Sentiment Analysis ◽  
Maximum Entropy ◽  
Opinion Mining ◽  
Naive Bayes ◽  
Daily Life ◽  
Naïve Bayes ◽  
Support Vector ◽  
Huge Amount

Community and portal websites like Twitter, Facebook, Tumbler, Instagram, and LinkedIn etc. have significant impact in our day-to-day life. One of the most popular micro-blogging platforms is twitter that can provide a huge amount of data which in future can be used for various applications of opinion mining like predictions, reviews, elections, marketing etc. The users use this platform to share their views, express sentiments on various events of their daily life. Previously, many researchers have worked with twitter sentiment analysis and compared various classifiers and got the accuracy below 82%. In this work for classifying tweets into sentiments, we have used various classifiers such as Naïve Bayes, Support Vector Machine and Maximum Entropy that segregate the positive and negative tweets. Using Bigram Collocation with classifiers, we’ve acquired 88.42% accuracy. KEYWORDS: Twitter; Sentiment Classification; Machine Learning; NLTK; Python; Naïve Bayes; Support Vector Machine (SVM); Maximum Entropy

scholarly journals Is the chronicity of HIV/AIDS fragile? Biomedicine, politics and sociability in an online social network

2020 ◽  
Vol 28 ◽  
Author(s):  
Lucas Pereira de Melo ◽  
Lumena Cristina de Assunção Cortez ◽  
Raul de Paiva Santos
Keyword(s):  
Social Network ◽  
Chronic Condition ◽  
Daily Life ◽  
Online Social Network ◽  
People Living With Hiv ◽  
Relevant Aspect ◽  
Mutual Help ◽  
Virtual Ethnography ◽  
Living With Hiv ◽  
Hiv Aids

Objective: to understand how the relationships between chronicity and politics shape sociability and mutual help among people living with HIV/AIDS. Method: This is a virtual ethnography in a closed group on Facebook. To collect the information, on-lineparticipant observation and documental analysis were utilized. 37 posts were analyzed using the softwareNVivo 12 Pro and the thematic coding technique. Results: Two thematic categories emerged: Do the treatment and time will take care of the rest: Mutual help and HIV/AIDS as a chronic condition; and Yes, there is danger around the corner, my dear: Politics, conflicts and sociability in the group. The most relevant aspect of this study concerns the evidence of the fragility of the discourse on the chronicity of HIV/AIDS. Conclusion: Through the analysis of sociability and mutual help produced among the members of the investigated group, it was possible to apprehend the ways in which, in their experiences on living with HIV/AIDS as a chronic condition, the relationships between health-disease, politics and time showed the dependence between chronicity and the State, and its impacts on daily life.

Sign in / Sign up

Export Citation Format

Share Document