Search results

A clickbait is a deceptive headline designed to boost ad revenue without presenting closely relevant content. There are numerous negative repercussions of clickbait, such as causing viewers to feel tricked and unhappy, causing long-term confusion, and even attracting cyber criminals. Automatic detection algorithms for clickbait have been developed to address this issue. The fact that there is only one semantic representation for the same term and a limited dataset in Chinese is a need for the existing technologies for detecting clickbait. This study aims to solve the limitations of automated clickbait detection in the Chinese dataset.

This study combines both to train the model to capture the probable relationship between clickbait news headlines and news content. In addition, part-of-speech elements are used to generate the most appropriate semantic representation for clickbait detection, improving clickbait detection performance.

This research successfully compiled a dataset containing up to 20,896 Chinese clickbait news articles. This collection contains news headlines, articles, categories and supplementary metadata. The suggested context-aware clickbait detection (CA-CD) model outperforms existing clickbait detection approaches on many criteria, demonstrating the proposed strategy's efficacy.

The originality of this study resides in the newly compiled Chinese clickbait dataset and contextual semantic representation-based clickbait detection approach employing transfer learning. This method can modify the semantic representation of each word based on context and assist the model in more precisely interpreting the original meaning of news articles.

This study aims to investigate how message sidedness affects the impact of fake news posted on social media on consumers' emotional responses.

The study involves a face-tracking experiment in which 198 participants were exposed to different fake news messages concerning the COVID-19 vaccine. Specifically, participants were exposed to fake news using (1) a one-sided negative fake news message in which the message was entirely unfavorable and (2) a two-sided fake news message in which the negative message was mixed with favorable information. Noldus FaceReader 7, an automatic facial expression recognition system, was used to recognize participants' emotions as they read fake news. The authors sampled 17,450 observations of participants' emotional responses.

The results provide evidence of the significant influence of message sidedness on consumers' emotional valence and arousal. Specifically, two-sided fake news positively influences emotional valence, while one-sided fake news positively influences emotional arousal.

The current study demonstrates that research on fake news posted on social media may particularly benefit from insights regarding the potential but often overlooked importance of strategic design choices in fake news messages and their impact on consumers' emotional responses.

Propaganda is a prevalent technique used in social media to intentionally express opinions or actions with the aim of manipulating or deceiving users. Existing methods for propaganda detection primarily focus on capturing language features within its content. However, these methods tend to overlook the information presented within the external news environment from which propaganda news originated and spread. This news environment reflects recent mainstream media opinions and public attention and contains language characteristics of non-propaganda news. Therefore, the authors have proposed a graph-based multi-information integration network with an external news environment (abbreviated as G-MINE) for propaganda detection.

G-MINE is proposed to comprise four parts: textual information extraction module, external news environment perception module, multi-information integration module and classifier. Specifically, the external news environment perception module and multi-information integration module extract and integrate the popularity and novelty into the textual information and capture the high-order complementary information between them.

G-MINE achieves state-of-the-art performance on both the TSHP-17, Qprop and the PTC data sets, with an accuracy of 98.24%, 90.59% and 97.44%, respectively.

An external news environment perception module is proposed to capture the popularity and novelty information, and a multi-information integration module is proposed to effectively fuse them with the textual information.

The dissemination of misleading and false information through media can jeopardize a company’s reputation, thus posing a threat to its stock and performance. Institutional investors are known to influence capital markets. Therefore, this paper investigates whether institutional investors engage in shaping the media sentiment stock nexus, stabilize company stocks and enhance performance.

We first investigate the effect of media sentiment on market reactions by using panel regression models. To examine the role of institutional investors, we design a quasi-experiment by exploiting the Financial Crisis of 2008 and go further by examining the heterogeneity across levels of institutional ownership. Due to risk-averse, investors may respond asymmetrically to pessimistic and positive sentiment. Accordingly, we split the sample into two sub-types, good news and bad news, based on keywords representing positive or negative content.

We find supportive evidence that institutional investors have impacts on how the markets react to media news, and the impacts are heterogeneous in the face of bad and good news. We conjecture that institutional investors act as a stabilizer of stock prices through media sentiment management.

This paper confirms the distinctive effects of institutional investors on capital markets, and uncovers the behind-the-scenes intervention and possible causal link running from institutional investors to media sentiment management. It contributes to the broad field of institutional investors' behavior, media news involvement in capital markets and market efficiency.

Stock market has always been lucrative for various investors. But, because of its speculative nature, it is difficult to predict the price movement. Investors have been using both fundamental and technical analysis to predict the prices. Fundamental analysis helps to study structured data of the company. Technical analysis helps to study price trends, and with the increasing and easy availability of unstructured data have made it important to study the market sentiment. Market sentiment has a major impact on the prices in short run. Hence, the purpose is to understand the market sentiment timely and effectively.

The research includes text mining and then creating various models for classification. The accuracy of these models is checked using confusion matrix.

Out of the six machine learning techniques used to create the classification model, kernel support vector machine gave the highest accuracy of 68%. This model can be now used to analyse the tweets, news and various other unstructured data to predict the price movement.

This study will help investors classify a news or a tweet into “positive”, “negative” or “neutral” quickly and determine the stock price trends.

Although the effects of both news sentiment and expectations on price in financial markets have now been extensively demonstrated, the jointness that these predictors can have in their effects on price has not been well-defined. Investigating causal ordering in their effects on price can further our understanding of both direct and indirect effects in their relationship to market price.

We use autoregressive distributed lag (ARDL) methodology to examine the relationship between agent expectations and news sentiment in predicting price in a financial market. The ARDL estimation is supplemented by Grainger causality testing.

In the ARDL models we implement, measures of expectations and news sentiment and their lags were confirmed to be significantly related to market price in separate estimates. Our results further indicate that in models of relationships between these predictors, news sentiment is a significant predictor of agent expectations, but agent expectations are not significant predictors of news sentiment. Granger-causality estimates confirmed the causal inferences from ARDL results.

Taken together, the results extend our understanding of the dynamics of expectations and sentiment as exogenous information sources that relate to price in financial markets. They suggest that the extensively cited predictor of news sentiment can have both a direct effect on market price and an indirect effect on price through agent expectations.

Even traditional financial management firms now commonly track behavioral measures of expectations and market sentiment. More complete understanding of the relationship between these predictors of market price can further their representation in predictive models.

This article extends the frequently reported bivariate relationship of expectations and sentiment to market price to examine jointness in the relationship between these variables in predicting price. Inference from ARDL estimates is supported by Grainger-causality estimates.

The ballooning health misinformation on social media raises grave concerns. Drawing upon the S-O-R (Stimulus-Organism-Response) model and the information processing literature, this study aims to explore (1) how social media health information seeking (S) affects health misinformation sharing intention (R) through the channel of health misperceptions (O) and (2) whether the mediation process would be contingent upon different information processing predispositions.

Data were collected from a survey comprising 388 respondents from the Chinese middle-aged or above group, one of China's most susceptible populations to health misinformation. Standard multiple linear regression models and the PROCESS Macro were adopted to examine the direct effect and the moderated mediation model.

Results bolstered the S-O-R-based mechanism, in which health misperceptions mediated social media health information seeking's effect on health misinformation sharing intention. As an indicator of analytical information processing, need for cognition (NFC) failed to moderate the mediation process. Contrarily, faith in intuition (FI), an indicator reflecting intuitive information processing, served as a significant moderator. The positive association between social media health information seeking and misperceptions was stronger among respondents with low FI.

This study sheds light on health misinformation sharing research by bridging health information seeking, information internalization and information sharing. Moreover, the authors extended the S-O-R model by integrating information processing predispositions, which differs this study from previous literature and advances the extant understanding of how information processing styles work in the face of online health misinformation. The particular age group and the Chinese context further inform context-specific implications regarding online health misinformation regulation.

The peer review history for this article is available at: https://publons.com/publon/10.1108/OIR-04-2023-0157.

Once a corporate crisis is entangled with a social issue, how consumers make sense of the crisis can be impacted by issue-based opinion polarization. This study investigates the underlying mechanisms as consumers go through this process. This study also examines whether corporate social advocacy (CSA) can be an effective crisis-response strategy for mitigating reputational loss.

Theoretical inquiries were empirically tested using an online experiment (N = 792). The experiment set the context in China, in a working-overtime-issue-related crisis. It had a 2 (online exposure: anti-issue opinion vs. pro-issue opinion) × 2 (CSA: absence vs. presence) between-subject design with a continuous variable (pre-existing issue attitudes) measured before the manipulation.

This study found that pre-existing issue attitudes can be directly and indirectly associated with corporate reputation, for the issue attitudes influence how consumers attribute crisis blame. Such a direct effect of pre-existing issue attitudes varies depending on which polarized opinion consumers were exposed to on social media. This study also found CSA to be a robust crisis response strategy, through multiple mechanisms, in protecting the corporate reputation.

Scholars are scarcely aware of the threats that issue-based opinion polarization poses to corporate reputation. This study serves as an early attempt to provide theoretical explanations. In addition to this, this study extends the current conceptual understandings of CSA during corporate crises that involve social issues while adding fresh insights into the established typology of crisis-response strategies.

Social media has made people better informed but also easier to manipulate. By using literature review and observing social media, the authors found a problem about echo chamber effect. The purpose of this paper is to know how the echo chamber affects the people who consume political news and the role of media diversity in it.

To conduct this study, the authors used a structured questionnaire on the Qualtrics platform to collect data from 183 participants. The authors collected data using a simple random technique. This study is based on the cross-sectional survey; the data collection period is from October to November 2023. The authors used the SPSS software to analyze the relationships between the variables and test the hypothesis.

This study found that, echo chamber is not affected by media diversity. Because of increased political interest, people will be less influenced by echo chambers. In addition, demographic factors affect political interest. People use search engines and social media sites instead of political websites when it comes to the consumption of political news online. People like to communicate with individuals who hold conflicting political views.

Researchers have not yet been able to gain a clear understanding of whether users are in an echo chamber or not and how they are interacting in that environment. Research on this topic is still going on from different perspectives. This study helped to clarify whether or not more media consumption will affect echo chambers. The possibility of being trapped in an echo chamber exists whether we use a single medium or a variety of media. The novelty of this study lies in the use of the echo chamber scale to investigate a thorough understanding of this word through the use of many factors.

This research analyzes the alignment of story framing between Samarco and news media following the dam disaster in Minas Gerais in November 2015. Drawing on framing theory as the underlying impetus, the study seeks to answer five major questions: RQ1: How did Samarco frame the mining tragedy in the aftermath of the dam collapse? RQ2: How did the news media frame the mining tragedy in the aftermath of the dam collapse? RQ3: Did the frames presented by Samarco and news media coincide? RQ4: Did the frames presented by Samarco and news media contradict? RQ5: What can be observed about the information flow and interaction between news media and the general public on social media? From a methods perspective, the study uses comparative textual analysis and NodeXL social network visualization to analyze the discourse around Samarco and information flow on social media in the aftermath of the tragedy. The results show that, while some social media content served as a forum for expressions of empathy toward survivors, social media content on Twitter mostly delivered a one-sided and positive view of the firm’s actions.