Rumor Classification through a Multimodal Fusion Framework and Ensemble Learning

2023 | Information Systems Frontiers | Citations: 0

Authors: Azri, Abderrazek; Favre, Cécile; Harbi, Nouria; Darmont, Jérôme; Noûs, Camille

Abstract: The proliferation of rumors on social media has become a major concern due to it ... Expand

Abstract: The proliferation of rumors on social media has become a major concern due to its ability to create a devastating impact. Manually assessing the veracity of social media messages is a very time-consuming task that can be much helped by machine learning. Most message veracity verification methods only exploit textual contents and metadata. Very few take both textual and visual contents, and more particularly images, into account. Moreover, prior works have used many classical machine learning models to detect rumors. However, although recent studies have proven the effectiveness of ensemble machine learning approaches, such models have seldom been applied. Thus, in this paper, we propose a set of advanced image features that are inspired from the field of image quality assessment, and introduce the Multimodal fusiON framework to assess message veracIty in social neTwORks (MONITOR), which exploits all message features by exploring various machine learning models. Moreover, we demonstrate the effectiveness of ensemble learning algorithms for rumor detection by using five metalearning models. Eventually, we conduct extensive experiments on two real-world datasets. Results show that MONITOR outperforms state-of-the-art machine learning baselines and that ensemble models significantly increase MONITOR’s performance. Collapse

Topics: Twitter social network Python microblog logistics management

Methods: computational algorithm machine learning experiment meta learning ensemble learning

A Signal Detection Theory Approach for Predicting Immunity to Pandemic Vaccine Fake News

2023 | HICSS | Citations: 0

Authors: Barajas, J.; John, R.

Abstract: Managing a contagious disease pandemic, such as , requires that the public unde ... Expand

Abstract: Managing a contagious disease pandemic, such as , requires that the public understand and cooperate with behavioral guidelines to reduce viral transmission. This research uses Signal Detection Theory (SDT) to explore how U.S. adults distinguish between true and false information related to COVID-19 vaccines. A total of 372 U.S. adults categorized 17 true and 17 false COVID-19 vaccine headlines. Item Response Theory analyses suggest that the ability to identify true information about the pandemic is a construct that can be reliably measured with our novel methodology. Signal Detection Theory analyses indicate high accuracy (AUC = 0.861), with no bias favoring either true or false responses. Overall, U.S. adults correctly classified 7 of 10 true and 8 of 10 false headlines. Multiple regression analyses on individual performance metrics reveal substantially lower accuracy among conservatives and those with lower scores on a measure of Actively Open-minded Thinking. Implications and limitations of these findings within the pandemic news context are discussed. Collapse

Topics: misinformation fake news pandemic social media covid 19

Methods: machine learning survey multiple linear regression survey design regression analysis method

Theories: signal detection theory

“JANE SENT ME THIS ARTICLE, SO IT MUST BE TRUE!” – HOW TIE STRENGTH AND EMOTIONAL TONE INFLUENCE INFORMATION BEHAVIOR

2023 | Americas Conference on Information Systems | Citations: 0

Authors: Buesching, Felix; Bruckner, Moritz; Frenzel-Piasentin, Adeline; Muench, Jan; Kwon, Youngjin; Thatcher, Jason B.; Veit, Daniel

Abstract: Fake news are a threat of the information age, yet many factors that determine ... Expand

Abstract: Fake news are a threat of the information age, yet many factors that determine their spread, such as emotional tone and tie strength, remain under-researched. Responding to calls for research, we developed an experimental study that explains the impact of emotional tone and tie strength in the context of instant messaging. We hypothesize effects on the willingness to fact-check and intention to share, mediated by sender credibility and news believability. Our results will contribute to the academic literature on various levels: we consider the emotional and relational dimensions of fake news sharing. Furthermore, we provide a multidimensional understanding of the emotionality of strong-tie contacts sharing fake news in a seemingly private and safe environment. For policymakers, we provide insights that help detect fake news, and we provide individuals with persuasion knowledge to self-protect against fake news. Collapse

Topics: fake news social media online chat Facebook Messenger

Methods: experiment descriptive statistic Student's t-test statistical hypothesis test

Social Norms and Misinformation Sharing of Politicized Products

2023 | Americas Conference on Information Systems | Citations: 0

Authors: Bui, Quang Neo; Moriuchi, Emi

Abstract: Misinformation has been on the rise, and in many cases, misinformation is inten ... Expand

Abstract: Misinformation has been on the rise, and in many cases, misinformation is intentionally shared for political reasons. This phenomenon first started with political news but now has spread in consumer products. To understand how misinformation sharing occurs differently between politized versus nonpoliticized products, we conducted an experiment and survey 800 respondents in an online crowdsourcing platform. The results show that for a politicized product, individual bias disposition and social norms indeed sway an individual's evaluation of information credibility, her trust and intention to share. However, this effect is not observed for non-politicized products. This call for more research to understand the role of social norms in stopping the spread of misinformation. Collapse

Topics: social norm social media misinformation crowdsourcing information exchange

Methods: parametric test structural equation modeling two-way ANOVA survey moderation analysis

A Theory-based Deep-Learning Approach to Detecting Disinformation in Financial Social Media

2023 | Information Systems Frontiers | Citations: 0

Authors: Chung, Wingyan; Zhang, Yinqiang; Pan, Jia

Abstract: The spreading of disinformation in social media threatens cybersecurity and unde ... Expand

Abstract: The spreading of disinformation in social media threatens cybersecurity and undermines market efficiency. Detecting disinformation is challenging due to large volumes of social media content and a rapidly changing environment. This research developed and validated a theory-based, novel deep-learning approach (called TRNN) to disinformation detection. Grounded in social and psychological theories, TRNN uses deep-learning and data-centric augmentation to enhance disinformation detection in financial social media. Temporal and contextual information is encoded as specific knowledge about human-validated disinformation, which was identified from our unique collection of 745,139 financial social media messages about four U.S. high-tech company stocks and their fine-grained trading data. TRNN uses multiple series of long short-term memory (LSTM) recurrent neurons to learn dynamic and hidden patterns to support disinformation detection. Our experimental findings show that TRNN significantly outperformed widely-used machine learning techniques in terms of precision, recall, F-score and accuracy, achieving consistently better classification performance in disinformation detection. A case study of Apple Inc.’s stock price movement demonstrates the potential usability of TRNN for secure knowledge management. The research contributes to developing novel approach and model, producing new information systems artifacts and dataset, and providing empirical findings of detecting online disinformation. Collapse

Topics: disinformation social media Twitter fake news usability

Methods: machine learning experiment design artifact deep learning recurrent neural network

Theories: psychological theory

Search & Verify: Misinformation and source evaluations in Internet search results

2023 | Decision Support Systems | Citations: 0

Authors: Dennis, Alan R.; Moravec, Patricia L.; Kim, Antino

Abstract: In response to online misinformation, source rating services evaluate thousands ... Expand

Abstract: In response to online misinformation, source rating services evaluate thousands of popular websites, mark them as reputable or disreputable, and provide detailed information explaining their evaluations. In this paper, we examine the effects of news source evaluations by experts as well as crowd-sourced information (i.e., Wikipedia) on beliefs in political news that appears in Internet search results. Through two online experiments, we inves­ tigate the effects of providing a simple source-evaluation flag or a flag with more detailed supporting information explaining the evaluation. We found that negative flags from expert fact-checkers reduced users' beliefs, and supporting information had no additional effect; in contrast, positive flags required information beyond the simple flag to have maximum effectiveness. Positive and negative crowd-sourced information had similar effects but was weaker than evaluations from experts. Thus, we conclude that providing additional information to support source evaluation flags is important to give users confidence in reputable websites. Collapse

Topics: Wikipedia internet technology crowdsourcing fake news blog

Methods: theory development linear regression analysis experiment post-hoc analysis survey

Theories: argumentation theory

USING TRANSACTION COST ECONOMICS SAFEGUARDING TO REDUCE THE DIFFUSION OF DISINFORMATION ON SOCIAL MEDIA

2023 | European Conference On Information Systems | Citations: 0

Authors: Eccles, David; Kurnia, Sherah; Geard, Nicholas; Dingler, Tilman

Abstract: Human users contribute to the spread of disinformation on Social Media. To redu ... Expand

Abstract: Human users contribute to the spread of disinformation on Social Media. To reduce the spread, we apply Transaction Cost Economics (TCE) Safeguarding, which penalises the sharing of disinformation. Using the economic theory TCE positions Social Media platforms as free markets, in which actors are motivated to protect their assets and peer reputation. We conducted a study exploring TCE Safeguarding as a market correction mechanism to change the disinformation diffusion behaviour of users. Our findings show that users will be less likely to post a comment and more likely to correct their previous disinformation diffusion actions when TCE Safeguarding is applied. Focusing on Social Media as a market rather than its individual components may provide a mechanism to address the "fake news" phenomenon. Collapse

Topics: disinformation social media user behavior fake news Facebook

Methods: survey experiment Mann Whitney U test nonparametric test economic model

Theories: economic theory transaction cost economics

Thinking Fast and Thinking Slow: Digital Devices' Effects on Cognitive Reflection

2023 | Journal of Management Information Systems | Citations: 0

Authors: Figl, Kathrin; Remus, Ulrich

Abstract: Informed by theoretical perspectives on working memory demands and devices' pote ... Expand

Abstract: Informed by theoretical perspectives on working memory demands and devices' potential to "prime" different types of cognitive processing, this paper investigates whether we tend to think "faster" and more intuitively, with less reflection when we use a smartphone instead of a personal computer (PC) or notebook. Three complementary experimental studies with a total of 823 participants reveal that the results of using such devices surface only when participants can select the smartphone as their preferred device. Controlling for potential confounding variables reveals no evidence of general differences between devices. Our findings caution against overemphasizing the importance of the type of device in thinking slow or fast and establish self-selection bias as an important factor in explaining such differences. This study contributes to clarifying the psychology of smartphone screens and how humans make choices when they are using these devices. Collapse

Topics: smartphone electronic mail social media decision making laptop computer

Methods: survey within subject experiment longitudinal research experiment hierarchical linear modeling

Theories: dual-system theory cognitive theory

Fake news believability: The effects of political beliefs and espoused cultural values

2023 | Information & Management | Citations: 0

Authors: Gupta, Manjul; Dennehy, Denis; Parra, Carlos M.; Mäntymäki, Matti; Dwivedi, Yogesh K

Abstract: Fake news has led to a polarized society as evidenced by diametrically opposed p ... Expand

Abstract: Fake news has led to a polarized society as evidenced by diametrically opposed perceptions of and reactions to global events such as the Coronavirus Disease 2019 (COVID-19) pandemic and presidential campaigns. Popular press has linked individuals’ political beliefs and cultural values to the extent to which they believe in false content shared on social networking sites (SNS). However, sweeping generalizations run the risk of helping exacerbate divisiveness in already polarized societies. This study examines the effects of individuals’ political beliefs and espoused cultural values on fake news believability using a repeated-measures design (that exposes individuals to a variety of fake news scenarios). Results from online questionnaire-based survey data collected from participants in the US and India help confirm that conservative individuals tend to exhibit increasing fake news believability and show that collectivists tend to do the same. This study advances knowledge on charac­ teristics that make individuals more susceptible to lending credence to fake news. In addition, this study explores the influence exerted by control variables (i.e., age, sex, and Internet usage). Findings are used to provide im­ plications for theory as well as actionable insights. Collapse

Topics: fake news information system use national culture individual characteristic WhatsApp

Methods: longitudinal research within subject experiment survey pilot survey psychometrics

Bridging digitalization to sustainable futures by going back to the “systems” paradigm in information systems

2023 | Americas Conference on Information Systems | Citations: 0

Authors: Hassan, Nik Rushdi

Abstract: This paper extends previous efforts to remedy the absence of "systems" theorizi ... Expand

Abstract: This paper extends previous efforts to remedy the absence of "systems" theorizing within the information systems (IS) field. It addresses the question, "Why is the IS field struggling with sustainability issues?" By leveraging on the nascent foundations built for going back to the systems approach in IS, this paper develops a model for how current efforts in digitalization and digital transformation can support the building of sustainable futures. The bridge that links digitalization to sustainable futures is built on the principles of the system paradigm that provides leverage points for positive interventions that will make a difference to efforts in sustainability. Collapse

Topics: misinformation fake news Twitter covid 19 digital transformation

Methods: theory development design science