Identification of rumour stances by considering network topology and social media comments

2020 ◽  
pp. 016555152094435
Author(s):  
Yongcong Luo ◽  
Jing Ma ◽  
Chai Kiat Yeo
Keyword(s):  
Social Media ◽  
Network Topology ◽  
Inverse Document Frequency ◽  
Online Social Media ◽  
Document Frequency ◽  
The Matrix ◽  
Special Attribute ◽  
Rapid Dissemination ◽  
Two Parameters ◽  
Vector Matrix

Online social media (OSM) has become a hotbed for the rapid dissemination of disinformation or faked news. In order to track and limit the spread of faked news, we study stance identification of comments posted on OSM, where the stance can denote the comment’s semantics. In this article, we propose a framework for identification of rumour stances, combining network topology and OSM comments. We construct a vector matrix of comments and words via OTI (optimisation term frequency–inverse document frequency). To better identify the stances, we introduce another vector matrix with novel or special attribute, that is, network topology among the users. Variant autoencoder (VAE) is then applied for dimensionality reduction and optimisation of these vector matrices which are then combined into an integrated matrix [Formula: see text], tempered by two parameters [Formula: see text] and [Formula: see text]. Finally, the matrix is fed into a neural network for final rumour stance identification. Experimental evaluations show that our proposed approach outperforms some state-of-the-art methods and achieves a high precision of 90.26% and F1-score of 88.58%.

Exploiting user network topology and comment semantic for accurate rumour stance recognition on social media

2020 ◽  
pp. 016555152097744
Author(s):  
Yongcong Luo ◽  
Jing Ma ◽  
Chai Kiat Yeo
Keyword(s):  
Social Media ◽  
Network Topology ◽  
Semantic Representation ◽  
Fake News ◽  
Inverse Document Frequency ◽  
Online Social Media ◽  
Document Frequency ◽  
Rapid Dissemination ◽  
Sentiment Score ◽  
Vector Matrix

Online social media (OSM) has become a hotbed for the rapid dissemination of disinformation or fake news. In order to recognise fake news and guide users of OSM, we focus on the stance recognition of comments, posted on OSM on the fake news-related users. In this article, we propose a framework for recognition of rumour stances (we set four categories –‘agree’, ‘disagree’, ‘neutral’ and ‘query’), combining network topology and comment semantic enhancement (CSE). We first construct a vector matrix of comments via a novel optimised term frequency–inverse document frequency (OTI). To better recognise stances, we employ another vector matrix with novel or special attributes which comprises the network topology of the OSM users derived from the random walk with restart (RWR) method. In addition, we set a weight parameter for each word in the comments to enhance comment semantic representation, where these parameters are tuned based on sentiment score, topology features and question format words. These vector matrices are optimised and combined into an integrated matrix whose transpose matrix is fed into a neural network (NN) for final rumour stance recognition. Experimental evaluations show that our approach achieves a high precision of 93.96% and F1-score of 92.02% which are superior to baselines and other existing methods.

AI-Based Cyberbullying Prevention in 5G Networks

2020 ◽  
Vol 11 (4) ◽  
pp. 1-20
Author(s):  
Sara Ramezanian ◽  
Tommi Meskanen ◽  
Valtteri Niemi
Keyword(s):  
Social Media ◽  
Psychological Effects ◽  
5G Networks ◽  
Inverse Document Frequency ◽  
Term Frequency ◽  
Online Social Media ◽  
Document Frequency ◽  
Policy Control ◽  
Cyberbullying Detection ◽  
Victims Of Bullying

Children and teenagers that have been victims of bullying can possibly suffer its psychological effects for a lifetime. With the increase of online social media, cyberbullying incidents have been increased as well. In this paper, the authors discuss how they can detect cyberbullying with AI techniques, using term frequency-inverse document frequency. The authors label messages as benign or bully. The authors want their method of cyberbullying detection to be privacy-preserving, such that the subscribers' benign messages should not be revealed to the operator. Moreover, the operator labels subscribers as normal, bully, and victim. The operator utilizes policy control in 5G networks to protect victims of cyberbullying from harmful traffic.

scholarly journals Sentiment Analysis with Machine Learning Methods on Social Media

2020 ◽  
Vol 9 (3) ◽  
pp. 5-15
Author(s):  
Muhammet Sinan Basarslan ◽  
Fatih Kayaalp
Keyword(s):  
Social Media ◽  
Sentiment Analysis ◽  
Support Vector ◽  
Inverse Document Frequency ◽  
Document Frequency ◽  
The Social ◽  
Vector Machines ◽  
Artificial Neural ◽  
Use Of The Internet ◽  
Python Programming

Social media has become an important part of our everyday life due to the widespread use of the Internet. Of the social media services, Twitter is among the most used ones around the world. People share their opinions by writing tweets about numerous subjects, such as politics, sports, economy, etc. Millions of tweets per day create a huge dataset, which drew attention of the data scientists to focus on these data for sentiment analysis. The sentiment analysis focuses to identify the social media posts of users about a specific topic and categorize them as positive, negative or neutral. Thus, the study aims to investigate the effect of types of text representation on the performance of sentiment analysis. In this study, two datasets were used in the experiments. The first one is the user reviews about movies from the IMDB, which has been labeled by Kotzias, and the second one is the Twitter tweets, including the tweets of users about health topic in English in 2019, collected using the Twitter API. The Python programming language was used in the study both for implementing the classification models using the Naïve Bayes (NB), Support Vector Machines (SVM) and Artificial Neural Networks (ANN) algorithms, and for categorizing the sentiments as positive, negative and neutral. The feature extraction from the dataset was performed using Term Frequency-Inverse Document Frequency (TF-IDF) and Word2Vec (W2V) modeling techniques. The success percentages of the classification algorithms were compared at the end. According to the experimental results, Artificial Neural Network had the best accuracy performance in both datasets compared to the others.

scholarly journals Sentiment Analysis for Detecting Cyberbullying Using TF-IDF and SVM

2020 ◽  
Vol 4 (6) ◽  
Author(s):  
Wahyu Adi Prabowo ◽  
Fitriani Azizah
Keyword(s):  
Social Media ◽  
System Model ◽  
Support Vector ◽  
Inverse Document Frequency ◽  
Document Frequency ◽  
Digital Development ◽  
Social Media Platforms ◽  
Python Programming ◽  
System Model Design

Social media has become a new method of today’s communication in a new digitalize era. Children and adults have used social media a lot in interacting with others. Therefore social media has shifted conventional communication into digital one. This digital development on social media is a serious problem that must be faced because it has been found that there are more and more acts of cyberbullying. This act of cyberbullying can attack the psychic, causing depression up to suicide. The dangers of cyberbullying are troubling and cause concern to the community. Therefore, this study will analyze the sentiment on the comments contained on social media to find out the value of sentiment from comments on social media platforms. The comment data will be processed at the preprocessing stage, Term Frequency-Inverse Document Frequency (TF-IDF), and the Support Vector Machine (SVM) classification method. Comment data to be classified as 1500 data taken using crawling data through libraries in python programming and divided into 80% data training and 20% data testing. Based on the results of the test, the accuracy value is 93%, the precision value is 95%, and the recall value is 97%. In this research, a system model design is also carried out where the system can be integrated with the browser to open a user page on the classification of comments that have been input into the system.

scholarly journals Impact of COVID-19 on Multiple Sclerosis Topic Discussion on Twitter

2021 ◽  
Author(s):  
Guido Giunti ◽  
Maëlick Claes ◽  
Enrique Dorronzoro Zubiete ◽  
Octavio Rivera-Romero ◽  
Elia Gabarron
Keyword(s):  
Multiple Sclerosis ◽  
Social Media ◽  
Comparative Analysis ◽  
Social Interaction ◽  
Healthcare Professional ◽  
Inverse Document Frequency ◽  
Original Dataset ◽  
Document Frequency ◽  
Neurologic Disorders ◽  
Emotional Aspects

Introduction: Multiple sclerosis (MS) is one of the world’s most common neurologic disorders. Social media have been proposed as a way to maintain and even increase social interaction for people with MS. The objective of this work is to identify and compare the topics on Twitter during the first wave of COVID-19 pandemic. Methods: Data was collected using the Twitter API between 9/2/2019 and 13/5/2020. SentiStrength was used to analyze data with the day that the pandemic was declared used as a turning point. Frequency-inverse document frequency (tf-idf) was used for each unigram and calculated the gains in tf-idf value. A comparative analysis of the relevance of words and categories among the datasets was performed. Results: The original dataset contained over 610k tweets, our final dataset had 147,963 tweets. After the 10th of march some categories gained relevance in positive tweets (“Healthcare professional”, “Chronic conditions”, “Condition burden”), while in negative tweets “Emotional aspects” became more relevant and “COVID-19” emerged as a new topic. Conclusions: Our work provides insight on how COVID-19 has changed the online discourse of people with MS.

Document Clustering Based on Fuzzy Similarity

2010 ◽  
Vol 29-32 ◽  
pp. 2620-2626
Author(s):  
Jing Li Zhou ◽  
Xue Jun Nie ◽  
Lei Hua Qin ◽  
Jian Feng Zhu
Keyword(s):  
Similarity Measure ◽  
Document Clustering ◽  
Similarity Measures ◽  
Experimental Results ◽  
Membership Degree ◽  
Inverse Document Frequency ◽  
Fuzzy Similarity ◽  
Document Frequency ◽  
The Matrix ◽  
Multiple Categories

This paper proposes a novel fuzzy similarity measure based on the relationships between terms and categories. A term-category matrix is presented to represent such relationships and each element in the matrix denotes a membership degree that a term belongs to a category, which is computed using term frequency inverse document frequency and fuzzy relationships between documents and categories. Fuzzy similarity takes into account the situation that one document belongs to multiple categories and is computed using fuzzy operators. The experimental results show that the proposed fuzzy similarity surpasses other common similarity measures not only in the reliable derivation of document clustering results, but also in document clustering accuracies.

Impact of Online Social Media on Consumer Decision Making: A Study in Dehradun

2012 ◽  
Vol 3 (5) ◽  
pp. 379-381
Author(s):  
Dr. Aruna Kumar Mishra ◽  
◽  
Narendra Kumar Narendra Kumar ◽  
Abhishek Sharma
Keyword(s):  
Decision Making ◽  
Social Media ◽  
Consumer Decision Making ◽  
Consumer Decision ◽  
Online Social Media

DERADICALISATION IDEAS IN SOCIAL MEDIA THROUGH THE RELIGIOUS-MULTICULTURAL THERAPY APPROACH TO THE DA'WAH CULTURE

2020 ◽  
Vol 24 (1) ◽  
pp. 58
Author(s):  
Anwar Hafidzi
Keyword(s):  
Social Media ◽  
Real World ◽  
Environmental Conditions ◽  
Islamic Law ◽  
Research Tool ◽  
Therapy Approach ◽  
The Real ◽  
Multicultural Therapy ◽  
Online Social Media ◽  
Library Research

This research begins with an understanding of the endemic radicalism of society, not only of the real world, but also of various online social media. This study showed that the avoidance of online radicalism can be stopped as soon as possible by accusing those influenced by the radical radicality of a secular religious approach. The methods used must be assisted in order to achieve balanced understanding (wasathiyah) under the different environmental conditions of the culture through recognizing the meaning of religion. The research tool used is primarily library work and the journal writings by Abu Rokhmad, a terrorist and radicalise specialist. The results of this study are that an approach that supports inclusive ism will avoid the awareness of radicalization through a heart-to-heart approach. This study also shows that radical actors will never cease to argue dramatically until they are able to grasp different views from Islamic law, culture, and families.Keywords: radicalism, deradicalization, multiculturalism, culture, religion, moderate.Penelitian ini berawal dari paham radikalisme yang telah mewabah di masyarakat, bukan hanya di dunia nyata, bahkan sudah menyusup di berbagai media sosial online. Penelitian ini menemukan bahwa cara menangkal radikalisme online dapat dilakukan pencegahan sedini mungkin melalui pendekatan konseling religius multikultural terhadap mereka yang terkena paham radikal radikal. Diantara teknik yang digunakan adalah melalui pemahaman tentang konsep agama juga perlu digalakkan agar memunculkan pemahaman yang moderat (wasathiyah) diberbagai keadaan lingkungan masyarakat. Metode yang digunakan untuk penelitian ini adalah library research dengan sumber utama adalah karya dan jurnal karya Abu Rokhmad seorang pakar dalam masalah terorisme dan radikalisme. Temuan penelitian ini adalah paham radikalisasi itu dapat dihentikan dengan pendekatan hati ke hati dengan mengedepankan budaya yang multikultural. Kajian ini juga membuktikan bahwa pelaku paham radikal tidak akan pernah berhenti memberikan argumen radikal kecuali mampu memahami perbedaan pendapat yang bersumber dari syariat Islam, lingkungan sosial, dan keluarga.Kata kunci: radikalisme, deradikalisasi, multikultural, budaya, agama, moderat.

Customer Revenue Sharing Program in Online Social Media

2012 ◽  
Author(s):  
Fouad H. Mirzaei ◽  
Fredrik Odegaard ◽  
Xinghao Yan
Keyword(s):  
Social Media ◽  
Revenue Sharing ◽  
Online Social Media
Sign in / Sign up

Export Citation Format

Share Document