Search results

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.

This study aims to explore the dissemination and evolutionary path of online public opinion from a crisis management perspective. By clarifying the influencing factors and dynamic mechanisms of online public opinion dissemination, this study provides insights into attenuating the negative impact of online public opinion and creating a favorable ecological space for online public opinion.

This research employs bibliometric analysis and CiteSpace software to analyze 302 Chinese articles published from 2006 to 2023 in the China National Knowledge Infrastructure (CNKI) database and 276 English articles published from 1994 to 2023 in the Web of Science core set database. Through literature keyword clustering, co-citation analysis and burst terms analysis, this paper summarizes the core scientific research institutions, scholars, hot topics and evolutionary paths of online public opinion crisis management research from both Chinese and international academic communities.

The results show that the study of online public opinion crisis management in China and internationally is centered on the life cycle theory, which integrates knowledge from information, computer and system sciences. Although there are differences in political interaction and stage evolution, the overall evolutionary path is similar, and it develops dynamically in the “benign conflict” between the expansion of the research perspective and the gradual refinement of research granularity.

This study summarizes the research results of online public opinion crisis management from China and the international academic community and identifies current research hotspots and theoretical evolution paths. Future research can focus on deepening the basic theories of public opinion crisis management under the influence of frontier technologies, exploring the subjectivity and emotionality of web users using fine algorithms and promoting the international development of network public opinion crisis management theory through transnational comparison and international cooperation.

The use of generative artificial intelligence (genAi) language models such as ChatGPT to write assignment text is well established. This paper aims to assess to what extent genAi can be used to obtain guidance on how to avoid detection when commissioning and submitting contract-written assignments and how workable the offered solutions are.

Although ChatGPT is programmed not to provide answers that are unethical or that may cause harm to people, ChatGPT’s can be prompted to answer with inverted moral valence, thereby supplying unethical answers. The authors tasked ChatGPT to generate 30 essays that discussed the benefits of submitting contract-written undergraduate assignments and outline the best ways of avoiding detection. The authors scored the likelihood that ChatGPT’s suggestions would be successful in avoiding detection by markers when submitting contract-written work.

While the majority of suggested strategies had a low chance of escaping detection, recommendations related to obscuring plagiarism and content blending as well as techniques related to distraction have a higher probability of remaining undetected. The authors conclude that ChatGPT can be used with success as a brainstorming tool to provide cheating advice, but that its success depends on the vigilance of the assignment markers and the cheating student’s ability to distinguish between genuinely viable options and those that appear to be workable but are not.

This paper is a novel application of making ChatGPT answer with inverted moral valence, simulating queries by students who may be intent on escaping detection when committing academic misconduct.

Sarcasm is a linguistic expression that usually carries the opposite meaning of what is being said by words, thus making it difficult for machines to discover the actual meaning. It is mainly distinguished by the inflection with which it is spoken, with an undercurrent of irony, and is largely dependent on context, which makes it a difficult task for computational analysis. Moreover, sarcasm expresses negative sentiments using positive words, allowing it to easily confuse sentiment analysis models. This paper aims to demonstrate the task of sarcasm detection using the approach of machine and deep learning.

For the purpose of sarcasm detection, machine and deep learning models were used on a data set consisting of 1.3 million social media comments, including both sarcastic and non-sarcastic comments. The data set was pre-processed using natural language processing methods, and additional features were extracted and analysed. Several machine learning models, including logistic regression, ridge regression, linear support vector and support vector machines, along with two deep learning models based on bidirectional long short-term memory and one bidirectional encoder representations from transformers (BERT)-based model, were implemented, evaluated and compared.

The performance of machine and deep learning models was compared in the task of sarcasm detection, and possible ways of improvement were discussed. Deep learning models showed more promise, performance-wise, for this type of task. Specifically, a state-of-the-art model in natural language processing, namely, BERT-based model, outperformed other machine and deep learning models.

This study compared the performance of the various machine and deep learning models in the task of sarcasm detection using the data set of 1.3 million comments from social media.

This research aims to explore whether or how organizations adopt people analytics (PA), its value and potential socio-technical factors that can enable or hinder PA projects by disrupting and reshaping human resource management. We do this by focusing on the Italian context.

We conduct a scoping review of data collected between 2018 and 2022 via Google Alerts (GA), a content change detection and notification service that is gaining popularity in scholarly research.

Our findings suggest that the diffusion of PA applications in Italy, especially those of a descriptive nature, is growing. Most of the existing PA applications are positioned in a positive technocratic light, envisioning the value of PA for both employees and organizations. The value for the latter appears to be direct, while the value for employees is realized through organizational initiatives. The findings also suggest that while enablers can vary between PA application types, the barriers, especially technological and environmental, are generic for both descriptive and predictive/prescriptive PA applications.

Theoretically, we propose a framework for analyzing PA applications, their values, enablers and barriers. Methodologically, we present and describe in detail a novel approach, drawing on GA that can be used to study PA in specific contexts. Practically, our study serves as a helpful point of reference for managers planning or implementing PA in Italy, for benchmarking PA in Italy over time and for comparative international studies.

Disinformation on social media is a serious issue. This study examines the effects of disinformation on COVID-19 vaccination decision-making to understand how social media users make healthcare decisions when disinformation is presented in their social media feeds. It examines trust in post owners as a moderator on the relationship between information types (i.e. disinformation and factual information) and vaccination decision-making.

This study conducts a scenario-based web survey experiment to collect extensive survey data from social media users.

This study reveals that information types differently affect social media users' COVID-19 vaccination decision-making and finds a moderating effect of trust in post owners on the relationship between information types and vaccination decision-making. For those who have a high degree of trust in post owners, the effect of information types on vaccination decision-making becomes large. In contrast, information types do not affect the decision-making of those who have a very low degree of trust in post owners. Besides, identification and compliance are found to affect trust in post owners.

This study contributes to the literature on online disinformation and individual healthcare decision-making by demonstrating the effect of disinformation on vaccination decision-making and providing empirical evidence on how trust in post owners impacts the effects of information types on vaccination decision-making. This study focuses on trust in post owners, unlike prior studies that focus on trust in information or social media platforms.

This study aims to investigate the role of negative media coverage of environmental, social and governance (ESG) issues in deterring tax avoidance. Inspired by media agenda-setting theory and legitimacy theory, this study hypothesises that an increase in ESG negative media coverage should cause a reputational drawback, leading companies to reduce tax avoidance to regain their legitimacy. Hence, this study examines a novel channel that links ESG and taxation.

This study uses panel regression analysis to examine the relationship between negative media coverage of ESG issues and tax avoidance among the largest European entities. This study considers different measures of tax avoidance and negative media coverage.

The results show that negative media coverage of ESG issues is negatively associated with tax avoidance, suggesting that media can act as an external monitor for corporate taxation.

The findings have implications for policymakers and regulators, which should consider tax transparency when dealing with ESG disclosure requirements. Tax disclosure should be integrated into ESG reporting.

The study has social implications related to the media, which act as watchdogs for firms’ irresponsible practices. According to this study’s findings, increased media pressure has the power to induce a better alignment between declared ESG policies and tax strategies.

This study contributes to the literature on the mechanisms that discourage tax avoidance and the literature on the relationship between ESG and taxation by shedding light on the role of media coverage.

This paper seeks to demonstrate the value of using social media to capture fashion trends, including the popularity of specific features of clothing, in order to improve the speed and accuracy of supply chain response in the era of fast fashion.

This study examines the role that text mining can play to improve trend recognition in the fashion industry. Researchers used n-gram analysis to design a social media trend detection tool referred to here as the Twitter Trend Tool (3Ts). This tool was applied to a Twitter dataset to identify trends whose validity was then checked against Google Trends.

The results suggest that Twitter data are trend representative and can be used to identify the apparel features that are most in demand in near real time.

The 3Ts introduced in this research contributes to the field of fashion analytics by offering a novel method for employing big data from social media to identify consumer preferences in fashion elements and analyzes consumer preferences to improve demand planning.

The 3Ts improves forecasting models and helps inform marketing campaigns in the apparel retail industry, especially in fast fashion.

Contemporary technological disruptions are espoused as though they stimulate sustainable growth in the built environment through the Green Internet of Things (G-IoT). Learning from discipline-specific experiences, this paper articulates recent advancements in the knowledge and concepts of G-IoT in relation to the construction and smart city sectors. It provides a scoping review for G-IoT as an overlooked dimension. Attention was paid to modern circularity, cleaner production and sustainability as key benefits of G-IoT adoption in line with the United Nations’ Sustainable Development Goals (UN-SDGs). In addition, this study also investigates the current application and adoption strategies of G-IoT.

This study uses the Preferred Reporting Items for Systematic and Meta-Analyses (PRISMA) review approach. Resources are drawn from Scopus and Web of Science repositories using apt search strings that reflect applications of G-IoT in the built environment in relation to construction management, urban planning, societies and infrastructure. Thematic analysis was used to analyze pertinent themes in the retrieved articles.

G-IoT is an overlooked dimension in construction and smart cities so far. Thirty-three scholarly articles were reviewed from a total of 82 articles retrieved, from which five themes were identified: G-IoT in buildings, computing, sustainability, waste management and tracking and monitoring. Among other applications, findings show that G-IoT is prominent in smart urban services, healthcare, traffic management, green computing, environmental protection, site safety and waste management. Applicable strategies to hasten adoption include raising awareness, financial incentives, dedicated work approaches, G-IoT technologies and purposeful capacity building among stakeholders. The future of G-IoT in construction and smart city research is in smart drones, building information modeling, digital twins, 3D printing, green computing, robotics and policies that incentivize adoption.

This study adds to the normative literature on envisioning potential strategies for adoption and the future of G-IoT in construction and smart cities as an overlooked dimension. No previous study to date has reviewed pertinent literature in this area, intending to investigate the current applications, adoption strategies and future direction of G-IoT in construction and smart cities. Researchers can expand on the current study by exploring the identified G-IoT applications and adoption strategies in detail, and practitioners can develop implementation policies, regulations and guidelines for holistic G-IoT adoption.

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.