Search results

The aim of this study is to investigate subject independent emotion recognition capabilities of EEG and peripheral physiological signals namely: electroocoulogram (EOG), electromyography (EMG), electrodermal activity (EDA), temperature, plethysmograph and respiration. The experiments are conducted on both modalities independently and in combination. This study arranges the physiological signals in order based on the prediction accuracy obtained on test data using time and frequency domain features.

DEAP dataset is used in this experiment. Time and frequency domain features of EEG and physiological signals are extracted, followed by correlation-based feature selection. Classifiers namely – Naïve Bayes, logistic regression, linear discriminant analysis, quadratic discriminant analysis, logit boost and stacking are trained on the selected features. Based on the performance of the classifiers on the test set, the best modality for each dimension of emotion is identified.

 The experimental results with EEG as one modality and all physiological signals as another modality indicate that EEG signals are better at arousal prediction compared to physiological signals by 7.18%, while physiological signals are better at valence prediction compared to EEG signals by 3.51%. The valence prediction accuracy of EOG is superior to zygomaticus electromyography (zEMG) and EDA by 1.75% at the cost of higher number of electrodes. This paper concludes that valence can be measured from the eyes (EOG) while arousal can be measured from the changes in blood volume (plethysmograph). The sorted order of physiological signals based on arousal prediction accuracy is plethysmograph, EOG (hEOG + vEOG), vEOG, hEOG, zEMG, tEMG, temperature, EMG (tEMG + zEMG), respiration, EDA, while based on valence prediction accuracy the sorted order is EOG (hEOG + vEOG), EDA, zEMG, hEOG, respiration, tEMG, vEOG, EMG (tEMG + zEMG), temperature and plethysmograph.

Many of the emotion recognition studies in literature are subject dependent and the limited subject independent emotion recognition studies in the literature report an average of leave one subject out (LOSO) validation result as accuracy. The work reported in this paper sets the baseline for subject independent emotion recognition using DEAP dataset by clearly specifying the subjects used in training and test set. In addition, this work specifies the cut-off score used to classify the scale as low or high in arousal and valence dimensions. Generally, statistical features are used for emotion recognition using physiological signals as a modality, whereas in this work, time and frequency domain features of physiological signals and EEG are used. This paper concludes that valence can be identified from EOG while arousal can be predicted from plethysmograph.

Social media platforms are highly visible platforms, so politicians try to maximize their benefits from their use, especially during election campaigns. On the other side, people express their views and sentiments toward politicians and political issues on social media, thus enabling them to observe their online political behavior. Therefore, this study aims to investigate user reactions on social media during the 2016 US presidential campaign to decide which candidate invoked stronger emotions on social media.

For testing the proposed hypotheses regarding emotional reactions to social media content during the 2016 presidential campaign, regression analysis was used to analyze a data set that consists of Trump’s 996 posts and Clinton’s 1,253 posts on Facebook. The proposed regression models are based on viral (likes, shares, comments) and emotional Facebook reactions (Angry, Haha, Sad, Surprise, Wow) as well as Russell’s valence, arousal, dominance (VAD) circumplex model for valence, arousal and dominance.

The results of regression analysis indicate how Facebook users felt about both presidential candidates. For Clinton’s page, both positive and negative content are equally liked, while Trump’s followers prefer funny and positive emotions. For both candidates, positive and negative content influences the number of comments. Trump’s followers mostly share positive content and the content that makes them angry, while Clinton’s followers share any content that does not make them angry. Based on VAD analysis, less dominant content, with high arousal and more positive emotions, is more liked on Trump’s page, where valence is a significant predictor for commenting and sharing. More positive content is more liked on Clinton’s page, where both positive and negative emotions with low arousal are correlated to commenting and sharing of posts.

Building on an empirical data set from Facebook, this study shows how differently the presidential candidates communicated on social media during the 2016 election campaign. According to the findings, Trump used a hard campaign strategy, while Clinton used a soft strategy.

This study aims to examine the impact of online travel reviews (OTR) on tourists’ intention to travel based on the stimulus–organism–response (SOR) model. Further, it explored the mediating effects of tourist trust in OTR.

In this direction, this study proposes and empirically validates a conceptual model after collecting data from 299 Indian consumers. Proposed hypotheses were tested by applying the structural equation modelling technique. Bootstrapping method was used for mediation testing.

The findings revealed that various attributes of OTR exert differential impacts on travel intention. The study also confirmed the mediating role of tourist trust in OTR.

This study offers significant practical implications for travel marketers. To capitalize on OTR, travel marketers are recommended to develop an effective and efficient online reviews management system. This will improve the quality, valence, quantity and consistency of OTR, which in turn will enhance tourist trust in OTR, leading to improved travel intention.

No empirical evidence has been traced on how OTR enhances tourist trust in OTR and their travel intention. In support of this, the present study proposes and empirically validates an extensive model to comprehend the role of various drivers of OTR in improving tourist trust in OTR, leading to enhanced travel intention based on the SOR model.

The escalating volume of electronic waste (e-waste) presents a significant environmental and health hazard, emphasizing the importance of promoting e-waste recycling. Therefore, this study aims to utilize a valence theory approach to comprehensively understand the factors influencing individuals' intention to recycle e-waste.

A survey-based research approach was employed to examine the factors influencing consumers' e-waste recycling intention. Data were collected through an online survey questionnaire from Malaysian individuals aged 18 and above. The hypotheses were tested using a sample of 300 respondents, employing partial least squares structural equation modeling as a symmetric analysis technique. Additionally, fuzzy-set Qualitative Comparative Analysis (fsQCA), an asymmetric analysis approach, was used to gain deeper insights. Non-probability purposive sampling was utilized in the sampling process.

The PLS-SEM analysis revealed that subjective norms and willingness to change significantly impact e-waste recycling intention. Furthermore, perceived convenience, environmental concerns and social media usage were found to support the intention to recycle e-waste. The fsQCA results enhanced the interpretation by uncovering intricate relationships among the antecedents and identifying specific configurations that accurately predict consumers' recycling intentions.

The practical implications of this study emphasize the need for policymakers and practitioners to raise awareness regarding the benefits of e-waste recycling, enhance convenience in the recycling process and strengthen personal and subjective norms to encourage individuals to recycle their e-waste.

This study's originality lies in its adoption of a valence theory framework to comprehend the intentions behind e-waste recycling, as well as its inclusion of control variables during the analysis. This unique approach enhances the understanding of factors influencing e-waste recycling intention and provides valuable insights for policymakers and practitioners in developing effective strategies to promote e-waste recycling behavior.

User-generated content (UGC) and service failure have attracted considerable marketing inquiry over the last two decades. Previous studies primarily focused on the outcome of service failure and the impact of UGC on perceived failure severity. This article departs from previous studies as it examines the moderating role of UGC on the relationship between service failure recovery (SFR) and customer–brand relationship.

Building on commitment-trust theory and from a phenomenological hermeneutical perspective, this article explores this phenomenon through the interpretation of 60 in-depth interviews with millennials from three European countries: Italy, France and the UK. An analysis of the data was conducted using a qualitative approach to understand the main constructs and relationships derived from the data.

This study conceptualises four distinct moderating characteristics of UGC in the SFR process: satisfaction with experience and brand, dissatisfaction with experience and brand, satisfaction with brand and dissatisfaction with brand. The insights from the responsiveness, empathetic response, counterfactual thinking and brand salience (RECB) framework contribute to research on UGC and shed light on the relationship between SFR and consumer–brand relationships in the fashion industry.

Overall, this study demonstrates that customer interactions with UGC significantly affect their responses to, and relationships with, a brand. The proposed framework opens up interesting avenues for future research on the moderating role of UGC on the relationship between SFR and customer–brand relationships.

This study aims to examine the influence of reward personalization on financing outcomes in the Industry 5.0 era, where reward-based crowdfunding meets the personalized needs of individuals.

The study utilizes a corpus of 218,822 crowdfunding projects and 1,276,786 reward options on Kickstarter to investigate the effect of reward personalization on investors’ willingness to participate in crowdfunding. The research draws on expectancy theory and employs quantitative and qualitative approaches to measure reward personalization. Quantitatively, the number of reward options is calculated by frequency; whereas text-mining techniques are implemented qualitatively to extract novelty, which serves as a proxy for innovation.

Findings indicate that reward personalization has an inverted U-shaped effect on investors’ willingness to participate, with investors in life-related projects having a stronger need for reward personalization than those interested in art-related projects. The pledge goal and reward text readability have an inverted U-shaped moderating effect on reward personalization from the perspective of reward expectations and reward instrumentality.

This study refines the application of expectancy theory to online financing, providing theoretical insight and practical guidance for crowdfunding platforms and financiers seeking to promote sustainable development through personalized innovation.

This study aims to establish a model for rapid and accurate emotion recognition in restaurant online reviews, thus advancing the literature and providing practical insights into electronic word-of-mouth management for the industry.

This study elaborates a hybrid model that integrates deep learning (DL) and a sentiment lexicon (SL) and compares it to five other models, including SL, random forest (RF), naïve Bayes, support vector machine (SVM) and a DL model, for the task of emotion recognition in restaurant online reviews. These models are trained and tested using 652,348 online reviews from 548 restaurants.

The hybrid approach performs well for valence-based emotion and discrete emotion recognition and is highly applicable for mining online reviews in a restaurant setting. The performances of SL and RF are inferior when it comes to recognizing discrete emotions. The DL method and SVM can perform satisfactorily in the valence-based emotion recognition.

These findings provide methodological and theoretical implications; thus, they advance the current state of knowledge on emotion recognition in restaurant online reviews. The results also provide practical insights into intelligent service quality monitoring and electronic word-of-mouth management for the industry.

This study proposes a superior model for emotion recognition in restaurant online reviews. The methodological framework and steps are elucidated in detail for future research and practical application. This study also details the performances of other commonly used models to support the selection of methods in research and practical applications.

This study is based on the heuristic-systematic model (HSM) to dynamically examine the effect of review variance on sales and the boundary conditions that mitigate this effect.

Based on the theoretical domain of HSM, a conceptual model is proposed that analyzes the nonlinear relationship between review variance and sales and the interaction and motivation factors that moderate these relationships. Review data from websites targeting the film industry in the USA and South Korea (Korea) were collected to empirically analyze the authors' hypothesis, and panel regression analysis was used for confirmation.

Moderated by interactive and motivational factors, review variance exhibits an inverse-U-shaped relationship with review variance. Specifically, as an interaction factor, review valence and owned social media (OSM) resulted in positive interaction effects, and as a motivation factor, the number of alternatives exhibited a positive interaction effect with review variance. The effect of review variance was less pronounced in the USA than in Korea.

The study outcomes reveal a nonlinear relationship between review variance and sales, thus supporting the contradictory findings of previous studies. This study contributes to the literature by using the HSM as a theoretical framework to verify various HSM mechanisms using online review data. This exploratory study also contributes to the international marketing literature by showing that the effects of review variance vary across cultures.

This paper aims to examine how content relevancy influences consumers’ preference to receive and share fake news. Further, it investigates how these receivers perceive the social image of the people who share fake news. Finally, this study examines how brand strength and valence and credibility of fake content influence consumer’s word-of-mouth recommendations, purchase intentions and attitude toward the brand.

Three experiments were conducted to test the hypotheses. The data was analyzed using a two-way analysis of variance and PROCESS techniques.

Findings indicate that people prefer to receive and share relevant content, even if it is fake. Sharing fake news conveys the sender’s sociability but also creates a negative perception of narcissism. Individuals are more likely to recommend a brand if the fake news is perceived as credible and positive (vs negative). Finally, brand-strength can help brands to negate the harmful effects of fake news.

Future research can explore the role of group dynamics, tie-strength and media richness (text, image and videos) in the dispersion of fake news and its impact on brands.

Marketers should communicate and educate consumers that sharing fake content can harm their social image, which can reduce information dispersion. Marketers should also improve brand-strength that can protect the brand against the adverse impact of fake news.

This study contributes to the emerging literature on fake news by studying the impact of fake news on consumer intentions and attitudes toward the brand, which are critical for the success of any brand.

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.