Adaptive Salp swarm optimization algorithms with inertia weights for novel fake news detection model in online social media

2021 ◽  
Author(s):  
Feyza Altunbey Ozbay ◽  
Bilal Alatas
Keyword(s):  
Social Media ◽  
Optimization Algorithms ◽  
Fake News ◽  
Swarm Optimization ◽  
Detection Model ◽  
Online Social Media

scholarly journals Fake News Detection on Social Media Using A Natural Language Inference Approach

2020 ◽  
Author(s):  
Amir Bidgoly ◽  
Hossein Amirkhani ◽  
Fariba Sadeghi
Keyword(s):  
Social Media ◽  
Natural Language ◽  
News Item ◽  
Support Vector ◽  
Statistical Features ◽  
Fake News ◽  
K Nearest Neighbors ◽  
News Sources ◽  
Online Social Media ◽  
Embedding Methods

Abstract Fake news detection is a challenging problem in online social media, with considerable social and political impacts. Several methods have already been proposed for the automatic detection of fake news, which are often based on the statistical features of the content or context of news. In this paper, we propose a novel fake news detection method based on Natural Language Inference (NLI) approach. Instead of using only statistical features of the content or context of the news, the proposed method exploits a human-like approach, which is based on inferring veracity using a set of reliable news. In this method, the related and similar news published in reputable news sources are used as auxiliary knowledge to infer the veracity of a given news item. We also collect and publish the first inference-based fake news detection dataset, called FNID, in two formats: the two-class version (FNID-FakeNewsNet) and the six-class version (FNID-LIAR). We use the NLI approach to boost several classical and deep machine learning models including Decision Tree, Naïve Bayes, Random Forest, Logistic Regression, k-Nearest Neighbors, Support Vector Machine, BiGRU, and BiLSTM along with different word embedding methods including Word2vec, GloVe, fastText, and BERT. The experiments show that the proposed method achieves 85.58% and 41.31% accuracies in the FNID-FakeNewsNet and FNID-LIAR datasets, respectively, which are 10.44% and 13.19% respective absolute improvements.

scholarly journals Detecting Fake News Over Job Posts via Bi-Directional Long Short-Term Memory (BIDLSTM)

2021 ◽  
Vol 16 (6) ◽  
pp. 1-18
Author(s):  
T. V. Divya ◽  
Barnali Gupta Banik
Keyword(s):  
Social Media ◽  
Performance Metrics ◽  
Short Term Memory ◽  
Word Embedding ◽  
Support Vector ◽  
Fake News ◽  
Short Term ◽  
Term Memory ◽  
Online Social Media ◽  
Long Short Term Memory

Fake news detection on job advertisements has grabbed the attention of many researchers over past decade. Various classifiers such as Support Vector Machine (SVM), XGBoost Classifier and Random Forest (RF) methods are greatly utilized for fake and real news detection pertaining to job advertisement posts in social media. Bi-Directional Long Short-Term Memory (Bi-LSTM) classifier is greatly utilized for learning word representations in lower-dimensional vector space and learning significant words word embedding or terms revealed through Word embedding algorithm. The fake news detection is greatly achieved along with real news on job post from online social media is achieved by Bi-LSTM classifier and thereby evaluating corresponding performance. The performance metrics such as Precision, Recall, F1-score, and Accuracy are assessed for effectiveness by fraudulency based on job posts. The outcome infers the effectiveness and prominence of features for detecting false news. .

scholarly journals Towards Combating Pandemic-Related Misinformation in Social Media

2021 ◽  
pp. 140-158
Author(s):  
Isa Inuwa-Dutse
Keyword(s):  
Social Media ◽  
Public Discourse ◽  
Preventive Measures ◽  
State Of The Art ◽  
Fake News ◽  
Social Distancing ◽  
The Public ◽  
Toxic Impact ◽  
Online Social Media ◽  
Social Media Platforms

Conventional preventive measures during pandemics include social distancing and lockdown. Such measures in the time of social media brought about a new set of challenges – vulnerability to the toxic impact of online misinformation is high. A case in point is COVID-19. As the virus propagates, so does the associated misinformation and fake news about it leading to an infodemic. Since the outbreak, there has been a surge of studies investigating various aspects of the pandemic. Of interest to this chapter are studies centering on datasets from online social media platforms where the bulk of the public discourse happens. The main goal is to support the fight against negative infodemic by (1) contributing a diverse set of curated relevant datasets; (2) offering relevant areas to study using the datasets; and (3) demonstrating how relevant datasets, strategies, and state-of-the-art IT tools can be leveraged in managing the pandemic.

scholarly journals Analysis on Fake News Detection Methodologies

2020 ◽  
Vol 9 (1) ◽  
pp. 1572-1575
Keyword(s):  
Social Media ◽  
News Media ◽  
Low Cost ◽  
Past Research ◽  
Online News ◽  
Easy Access ◽  
Accurate Information ◽  
Fake News ◽  
The Real ◽  
Online Social Media

Fake news is a coinage often used to refer to fabricated news that uses eye-catching headlines for increased sales rather than legitimate well-researched news, spread via online social media. Emergence of fake news has been increased with the immense use of online news media and social media. Low cost, easy access and rapid dissemination of information lead people to consume news from social media. Since the spread rate of these contents are faster it becomes difficult to identify the fake news from the accurate information. People can download articles from sites, share the content, re-share from others and by the end of the day the false information has gone far from its original site that it becomes very difficult to compare with the real news. It is a long standing problem that affects the digital social media due to its serious threats of misleading information, it creates an immense impact on the society. Hence the identification of such news are relevant and so certain measures needs to be taken in order to reduce or distinguish between the real and fake news. This paper provides a survey on recent past research papers done on this domain and provides an idea on different techniques on machine learning and deep learning that could help in the identification of fake and real news.

scholarly journals KEBIJAKAN PEMERINTAH SURABAYA DALAM MENANGANI BERITA HOAX (Studi kasus di kota Surabaya)

2020 ◽  
Vol 5 (1) ◽  
pp. 67
Author(s):  
Pitri Megasari
Keyword(s):  
Social Media ◽  
Government Policy ◽  
Qualitative Data ◽  
City Government ◽  
Government Policies ◽  
Fake News ◽  
Political Issues ◽  
The Public ◽  
Online Social Media ◽  
False News

Abstract: This paper discusses how government policies in counteracting hoax news in the community through social media. Sometime lately more rampant news about the spread of fake news or hoaxes through online social media such as Twitter, Facebook, Instagram and YouTube. The formulation of the problem here is how the Surabaya government policy to overcome or handle the existence of false news or hoaxes in the Surabaya community. The research method for this type of research is qualitative. The data used are qualitative data, expressed in words or sentences. This false information or hoax was made deliberately because it was to influence the public because of the increasingly widespread stimulant factors such as social and political issues. Social media is now widely used to negative things like one of the accounts that spread hoax information just to increase the popularity of the account or want to be viral by spreading hoax news. Social media makes it easier for us to interact with many people and easier to convey information. But this social media makes a lot of people addicted and many social groups appear that deviate from the norms that exist in the Surabaya city government trying continuously to deal with fake news or hoaxes that are widely spread among the citizens of Surabaya.Keywords: Government Policy, Hoax News, Society

scholarly journals Spread of health-related fake news in Tamil social media - A pilot study

2019 ◽  
Vol 1 ◽  
pp. 21-24
Author(s):  
R Dharshanram ◽  
P D Madan Kumar ◽  
P Iyapparaj
Keyword(s):  
Social Media ◽  
Oral Cancer ◽  
News Media ◽  
Social Media Analytics ◽  
Fake News ◽  
Enterprise Application ◽  
Online Social Media ◽  
Health Related ◽  
Educational Campaign ◽  
Gum Disease

Introduction: Fake news is a type of propaganda that consists of deliberate misinformation or hoaxes spread through traditional print and broadcast news media or online social media. Fake news concerning health subject is not a new phenomenon - its roots are probably as old as healthcare itself. Aim: This study aims to measure the volume of shares concerning health-related fake news in Tamil language social media. Materials and Methods: Analysis was performed employing the BuzzFeed Enterprise Application available through its website. BuzzFeed is a social media analytics and curation tool for content marketers. The data were obtained for 15 most commonly shared pages concerning four keywords, namely vaccinations, oral cancer, gum disease, and dental caries from May 1, 2018, to May 15, 2018, in Tamil language, the local vernacular. Results: The topic most contaminated with fake news was vaccinations (80%) followed by oral cancer and gum disease (both in 60%). Altogether, links containing fake news were shared 272 times in 15 days and accounted for 40% of the studied material. Conclusion: Action could be taken to scientifically evaluate sources of the most frequently shared medical myths. As shown above, some topics were generally free of fake news, whereas others were extremely biased and filled with fallacies. Thus, an extensive educational campaign (not only in social media) for the latter should be implemented.

scholarly journals Influencing Opinions through False Online Information : A Study

2019 ◽  
pp. 443-449
Author(s):  
Baldev Singh
Keyword(s):  
Social Media ◽  
News Media ◽  
Online Information ◽  
Fake News ◽  
False Information ◽  
Detection Algorithms ◽  
Online Social Media ◽  
The People ◽  
Information Detection ◽  
Fake Reviews

Online Social media generates lot of information now-a-days. It is not legitimate information so there are the chances of fake and false information produced using social media. It is very alarming that majority of the people getting news from social media which is very much prone to false information in comparison to traditional news media which is very dangerous to the society. One of the primary reasons to influence opinion through false information is to earn money, name or fame. In this study, the focus is on to highlight false information generated through fake reviews, fake news and hoaxes based on web & social media. It summarized various False information spreading Mechanisms, False Information Detection Algorithms, Mining Techniques for Online False Information to detect and prevent false online information.

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.

Sign in / Sign up

Export Citation Format

Share Document