PurposeDepression is a mental health problem characterized by a persistent sense of sadness and loss of interest. EEG signals are regarded as the most appropriate instruments for diagnosing depression because they reflect the operating status of the human brain. The purpose of this study is the early detection of depression among people using EEG signals.Design/methodology/approach(i) Artifacts are removed by filtering and linear and non-linear features are extracted; (ii) feature scaling is done using a standard scalar while principal component analysis (PCA) is used for feature reduction; (iii) the linear, non-linear and combination of both (only for those whose accuracy is highest) are taken for further analysis where some ML and DL classifiers are applied for the classification of depression; and (iv) in this study, total 15 distinct ML and DL methods, including KNN, SVM, bagging SVM, RF, GB, Extreme Gradient Boosting, MNB, Adaboost, Bagging RF, BootAgg, Gaussian NB, RNN, 1DCNN, RBFNN and LSTM, that have been effectively utilized as classifiers to handle a variety of real-world issues.Findings1. Among all, alpha, alpha asymmetry, gamma and gamma asymmetry give the best results in linear features, while RWE, DFA, CD and AE give the best results in non-linear feature. 2. In the linear features, gamma and alpha asymmetry have given 99.98% accuracy for Bagging RF, while gamma asymmetry has given 99.98% accuracy for BootAgg. 3. For non-linear features, it has been shown 99.84% of accuracy for RWE and DFA in RF, 99.97% accuracy for DFA in XGBoost and 99.94% accuracy for RWE in BootAgg. 4. By using DL, in linear features, gamma asymmetry has given more than 96% accuracy in RNN and 91% accuracy in LSTM and for non-linear features, 89% accuracy has been achieved for CD and AE in LSTM. 5. By combining linear and non-linear features, the highest accuracy was achieved in Bagging RF (98.50%) gamma asymmetry + RWE. In DL, Alpha + RWE, Gamma asymmetry + CD and gamma asymmetry + RWE have achieved 98% accuracy in LSTM.Originality/valueA novel dataset was collected from the Central Institute of Psychiatry (CIP), Ranchi which was recorded using a 128-channels whereas major previous studies used fewer channels; the details of the study participants are summarized and a model is developed for statistical analysis using N-way ANOVA; artifacts are removed by high and low pass filtering of epoch data followed by re-referencing and independent component analysis for noise removal; linear features, namely, band power and interhemispheric asymmetry and non-linear features, namely, relative wavelet energy, wavelet entropy, Approximate entropy, sample entropy, detrended fluctuation analysis and correlation dimension are extracted; this model utilizes Epoch (213,072) for 5 s EEG data, which allows the model to train for longer, thereby increasing the efficiency of classifiers. Features scaling is done using a standard scalar rather than normalization because it helps increase the accuracy of the models (especially for deep learning algorithms) while PCA is used for feature reduction; the linear, non-linear and combination of both features are taken for extensive analysis in conjunction with ML and DL classifiers for the classification of depression. The combination of linear and non-linear features (only for those whose accuracy is highest) is used for the best detection results.

PurposeThe study aims to overview the different types of internal-led cyber fraud that have gained mainstream attention in recent major-value fraud events involving prominent Indian banks. The authors attempted to identify and classify cyber frauds and its drivers and correlate them for optimal mitigation planning.Design/methodology/approachThe methodology opted for the identification and classification is through a detailed literature review and focus group discussion with risk and vigilance officers and cyber cell experts. The authors assessed the future of cyber fraud in the Indian banking business through the machine learning–based k-nearest neighbor (K-NN) approach and prioritized and predicted the future of cyber fraud. The predicted future revealing dominance of a few specific cyber frauds will help to get an appropriate fraud prevention model, using an associated parties centric (victim and offender) root-cause approach. The study uses correlation analysis and maps frauds with their respective drivers to determine the resource specific effective mitigation plan.FindingsFinally, the paper concludes with a conceptual framework for preventing internal-led cyber fraud within the scope of the study. A cyber fraud mitigation ecosystem will be helpful for policymakers and fraud investigation officers to create a more robust environment for banks through timely and quick detection of cyber frauds and prevention of them.Research limitations/implicationsAdditionally, the study supports the Reserve Bank of India and the Government of India's launched cyber security initiates and schemes which ensure protection for the banking ecosystem i.e. RBI direct scheme, integrated ombudsman scheme, cyber swachhta kendra (botnet cleaning and malware analysis centre), National Cyber Coordination Centre (NCCC) and Security Monitoring Centre (SMC).Practical implicationsStructured and effective internal-led plans for cyber fraud mitigation proposed in this study will conserve banks, employees, regulatory authorities, customers and economic resources, save bank authorities’ and policymakers’ time and money, and conserve resources. Additionally, this will enhance the reputation of the Indian banking industry and extend its lifespan.Originality/valueThe innovative insider-led cyber fraud mitigation approach quickly identifies cyber fraud, prioritizes it, identifies its prominent root causes, map frauds with respective root causes and then suggests strategies to ensure a cost-effective and time-saving bank ecosystem.

PurposeThe widespread acceptance of various social platforms has increased the number of users posting about various services based on their experiences about the services. Finding out the intended ratings of social media (SM) posts is important for both organizations and prospective users since these posts can help in capturing the user’s perspectives. However, unlike merchant websites, the SM posts related to the service-experience cannot be rated unless explicitly mentioned in the comments. Additionally, predicting ratings can also help to build a database using recent comments for testing recommender algorithms in various scenarios.Design/methodology/approachIn this study, the authors have predicted the ratings of SM posts using linear (Naïve Bayes, max-entropy) and non-linear (k-nearest neighbor, k-NN) classifiers utilizing combinations of different features, sentiment scores and emotion scores.FindingsOverall, the results of this study reveal that the non-linear classifier (k-NN classifier) performed better than the linear classifiers (Naïve Bayes, Max-entropy classifier). Results also show an improvement of performance where the classifier was combined with sentiment and emotion scores. Introduction of the feature “factors of importance” or “the latent factors” also show an improvement of the classifier performance.Originality/valueThis study provides a new avenue of predicting ratings of SM feeds by the use of machine learning algorithms along with a combination of different features like emotional aspects and latent factors.

PurposeThis study aims to identify the challenges in the healthcare industry as it adopts an omnichannel setup in an emerging economy context. Further, the study determines the scope of blockchain in addressing these challenges.Design/methodology/approachThe study uses a qualitative approach to understand the challenges in the omnichannel healthcare industry and know the scope of blockchain in building an omnichannel healthcare system. In the first stage, it did an in-depth analysis of the extant literature, followed by a Delphi study with 24 healthcare experts.FindingsThe study presents the current challenges in the omnichannel healthcare sector in an emerging economy. Further, it develops a novel conceptual framework for blockchain adoption in the omnichannel healthcare industry. The study also presents propositions that will help healthcare service providers enhance decision-making concerning the adoption of blockchain in the healthcare industry.Research limitations/implicationsThe research results may lack generalizability due to the exploratory approach and emerging economies context. Theoretically, in this study, the authors extend the theory of swift trust and organization information processing theory in an omnichannel healthcare context.Practical implicationsThe propositions provided in this paper can help healthcare managers make strategic decisions on the scope of adoption of blockchain for omnichannel healthcare.Originality/valueThis study explores the understudied area of challenges in omnichannel healthcare and the scope of blockchain for omnichannel healthcare in an emerging economy context.

PurposeCyberchondria refers to the repeated and excessive search for health-related information online, associated with increased health anxiety. This paper utilizes the protection motivation theory to investigate the negative behavioral consequences of cyberchondria that pose health risks to users, such as trust in the physician, propensity to self-medicate, and therapy compliance.Design/methodology/approachThe data for the study were collected from a sample of 317 participants in India using an online survey and form. The analysis was conducted using structural equation modeling.FindingsCyberchondria negatively affects the trust in physician and positively affects the propensity to self-medicate. Trust in physician negatively affects the propensity to self-medicate and positively affects therapy compliance. Furthermore, trust in physician partially mediates the relationship between cyberchondria and the propensity to self-medicate and completely mediates the relationship between cyberchondria and therapy compliance. Cyberchondria has no direct significant effect on therapy compliance.Research limitations/implicationsResearchers need to examine other behavioral or psychological factors affected by the reduced trust in physicians due to cyberchondria.Practical implicationsPhysicians and health care providers should refocus on patients with cyberchondria and regain their trust through quality interactions and services. Policymakers may consider regulating online health information publication to set the standards of information quality and source. Websites and platforms publishing health information online should distinctly label verified information.Originality/valueThis study investigates the damaging effects of cyberchondria's behavioral consequences that pose health risks to users.

PurposeNowadays, technostress is a common problem for many organisations. The purpose of this research is to investigate the underlying mechanisms under which enterprise social networks (ESNs) leads to technostress and their consequences.Design/methodology/approachThe authors collected data from 242 employees working in research and development (R&D) centres in India and analysed the data using partial least squares structural equation modelling (PLS-SEM).FindingsThe findings of the study contribute to the growing body of knowledge in “dark side of social media research” by researching the phenomenon of higher use of ESNs in organisations and the consequences while theoretically delineating the effect of social, hedonic and cognitive use of ESNs in organisations on technostress, thus extending prior research on adverse impact of social media and technostress research. The results revealed that both ESNs’ need and technostress is adversely related to mental health, performance and greater turnover intention, and perceived organisation support (POS) played a moderating role in this relationship such that with higher POS, employee turnover intention reduces. By uncovering the role of POS as a potential moderator, the findings provide empirical evidence for POS and technostress in organisations, thus offering practical implications for the ESNs strategists, managers and practitioners to develop ESNs’ usage policies to avoid adverse outcomes of technostress in organisations.Research limitations/implicationsThis research advances theoretical understanding of the relationship between ESNs, technostress, mental health, performance and turnover” intention while contributing extensively to the technostress literature and to the scholarship of ESNs. In addition, by uncovering the role of perceived organisational support as a potential moderator, this study contributes to the existing literature on POS.Practical implicationsThe empirically tested model delivered by this research will enable organisations to understand different excessive usage patterns of ESNs at work, which contribute to negative outcomes for organisations and employees. The findings support the maintenance of social life at work affecting better employee mental health, and the application of cognitive use of ESNs can reduce technostress. Hence, organisational strategies should implement employee policies and interventions that facilitate better work–social life and well-being, simultaneously encouraging usage of ESNs largely for work-related information transmission and sharing within the organisations.Originality/valueThis study constructed a moderated-mediation model by introducing the potential mediating effect of technostress, mental health and performance and the moderating effect of POS to reveal the mechanism through which ESNs related to technostress, mental health, performance and turnover intention in the Indian context.

PurposeThe alternative arrangements to traditional employment have become a promising area in the gig economy with the technological advancements dominating every work. The purpose of this paper is to explore the barriers to the entry of gig workers in gig platforms pertaining to the food delivery sector. It proposes a framework using interpretive structural modelling (ISM) for which systematic literature review is done to extract the variables. This analysis helps to examine the relationship between the entry barriers to gig platforms. The study further proposes strategies to reduce the entry barriers in gig sector which would help to enhance productivity and generate employment opportunities.Design/methodology/approachThe study uses interpretive structural model (ISM) to ascertain the relationship between various entry barriers of the gig workers to the gig platforms. It also validates the relationship and understand the reasons of their association along with MICMAC analysis. The model was designed by consulting the gig workers and the experts allied to food delivery gig platforms namely Zomato and Swiggy.FindingsIt was observed that high competition, longer login hours and late-night deliveries are the significant barriers with high driving power and low dependence power. Poor payment structures and strict terms and conditions for receiving the incentives are interdependent on each other and have moderate driving and dependence power. The expenses borne by the gig workers, such as Internet, fuel and vehicle maintenance expenses have high dependence power and low driving power. Hence, they are relatively less significant than other barriers.Research limitations/implicationsThe study is confined to food delivery sector of India, without considering other important sectors of gig economy for generalizing the framework. As the study is based on forming an ISM framework through literature review only, it does not consider other research methods for analysing the entry barriers to the gig platforms.Practical implicationsThe study attempts to dig out the low entry barriers for gig workers in food delivery platforms as there is a dearth of analysis of these factors. This study would weave them using ISM framework to help the gig platforms overcome these barriers at various levels, thus adding to the body of literature.Originality/valueThe study discusses the need for understanding relationship between the entry barriers in the form of ISM model to identify the dependent and driving factors of the same.

Purpose“Fake news” or misinformation sharing using social media sites into public discourse or politics has increased dramatically, over the last few years, especially in the current COVID-19 pandemic causing concern. However, this phenomenon is inadequately researched. This study examines fake news sharing with the lens of stimulus-organism-response (SOR) theory, uses and gratification theory (UGT) and big five personality traits (BFPT) theory to understand the motivations for sharing fake news and the personality traits that do so. The stimuli in the model comprise gratifications (pass time, entertainment, socialization, information sharing and information seeking) and personality traits (agreeableness, conscientiousness, extraversion, openness and neuroticism). The feeling of authenticating or instantly sharing news is the organism leading to sharing fake news, which forms the response in the study.Design/methodology/approachThe conceptual model was tested by the data collected from a sample of 221 social media users in India. The data were analyzed with partial least squares structural equation modeling to determine the effects of UGT and personality traits on fake news sharing. The moderating role of the platform WhatsApp or Facebook was studied.Findings The results suggest that pass time, information sharing and socialization gratifications lead to instant sharing news on social media platforms. Individuals who exhibit extraversion, neuroticism and openness share news on social media platforms instantly. In contrast, agreeableness and conscientiousness personality traits lead to authentication news before sharing on the social media platform.Originality/value This study contributes to social media literature by identifying the user gratifications and personality traits that lead to sharing fake news on social media platforms. Furthermore, the study also sheds light on the moderating influence of the choice of the social media platform for fake news sharing.

PurposeOpen government data (OGD) are considered as a technology capable of promoting transparency openness, and accountability, which in turn has a positive impact on innovation activities and creates responsive government, collaboration, cooperation, co-creation and participation. The purpose of this paper is to explore the adoption of OGD and open data portals among students, in an attempt to discover how governments can improve their actions in this respect.Design/methodology/approachThis study develops a behavioural intention-based analysis using constructs from the Unified Theory of Acceptance and Use of Technology, which is supplemented with additional constructs that meet the purpose of the study. In total, ten constructs divided into 33 items constituted the input for our study. Input data for the developed model have been collected through a structured questionnaire distributed between bachelor's and master's level students in three countries – the Czech Republic, India and Latvia. A structural equation modelling technique was used to analyse the relationships between variables of the model and test the nine hypothesis defined.FindingsSix constructs have been identified to facilitate significant relationships with behavioural intention. The analysis of the results of the three countries allows us to draw more objective conclusions in respect to the aim of the study and to reveal country-specific aspects that need to be addressed in the future.Originality/valueThis study adds to the existing literature few theoretical and practical aspects. It highlights the role of open data portals as a central point of OGD infrastructures. It enables governments to understand the relationships among the related constructs, improving their actions and modifying their data infrastructures accordingly.

PurposeThe aim of this research is to investigate the factors influencing the adoption of digital payments by the semi-rural women in India.Design/methodology/approachThe study extended the factors of unified theory of acceptance and use of technology UTAUT-2, with perceived credibility and self-determination theory to understand the use behaviour of the rural Indian women. The study checked the mediating role of some constructs besides testing the direct relationship. The study was conducted in the rural parts of the adjoining areas of Delhi, where the women from different states, education and financial background live. The research model was empirically tested on 568 respondents using structural equation modelling (SEM) technique.FindingsThe research model was able to explain 72.6% variance in the user behaviour variable. Effort expectancy, habit, facilitating conditions as well as perceived competence emerged out to be significant determinants of use behaviour. Besides these direct relationships, two constructs, habit as well as facilitating conditions were found to partially mediate the relationship between behavioural intention and behaviour.Originality/valueThis study provides some very critical clues for the companies providing digital payment services, by highlighting the significant factors explaining the technology adoption by semi-rural women. The companies must devise suitable marketing strategies to inculcate trust in mind of perspective customers towards their companies as well as the service provided by them. The role of simple digital platform, that is easy to learn and use, is also an important element in determining the technology adoption.

PurposeThe purpose of this study is to examine the dark side of instant messaging from the technological and societal perspectives.Design/methodology/approachWith the help of literature review and different theories, a model has been developed conceptually. Later the model has been validated using statistical method. The authors have used 304 responses from the survey method, and this sample has been used to statistically validate the conceptual model.FindingsThis paper has been able to explicitly investigate and identify how different instant messaging platforms such as WhatsApp, WeChat in the form of electronic word of mouth (e-WOM) are contributing toward increase of mob lynching cases. The paper also highlights the important to have effective and enforceable regulation to regulate instant messaging services to the citizens.Research limitations/implicationsThe findings cannot be generalized as the data is collected from India only. Moreover, the study is cross-sectional in nature. To get the comprehensive results, a longitudinal study needs to be conducted. This study considered seven constructs with one moderator. Having more predictors with other boundary conditions might have increased the explanative power of the model.Practical implicationsInstant messaging platforms such as WhatsApp, WeChat and so on are disseminating quick unverified information to the common people. This information sometimes is disseminated in inappropriate and exaggerated forms. This makes the instant messaging (WhatsApp) users' sentiment readily heated in some cases. They take such an action as mob lynching. This study determines the predictors of mob lynching along with the moderator impact of instant messaging in the society.Originality/valueThere are only a few studies those have explored the dark side of instant messaging. The proposed theoretical model is a unique model, which shows the predictors of mob lynching along with the negative consequences of the instant messaging (WhatsApp) in the society. From this perspective, this study can be considered as a unique study.

Purpose – The purpose of this paper is to analyse the author self-citation behavior in the field of Library and Information Science. Various factors governing the author self-citation behavior have also been studied. Design/methodology/approach – The 2012 edition of Social Science Citation Index was consulted for the selection of LIS journals. Under the subject heading “Information Science and Library Science” there were 84 journals and out of these 12 journals were selected for the study based on systematic sampling. The study was confined to original research and review articles that were published in select journals in the year 2009. The main reason to choose 2009 was to get at least five years (2009-2013) citation data from Web of Science Core Collection (excluding Book Citation Index) and SciELO Citation Index. A citation was treated as self-citation whenever one of the authors of citing and cited paper was common, i.e., the set of co-authors of the citing paper and that of the cited one are not disjoint. To minimize the risk of homonyms, spelling variances and misspelling in authors’ names, the authors compared full author names in citing and cited articles. Findings – A positive correlation between number of authors and total number of citations exists with no correlation between number of authors and number/share of self-citations, i.e., self-citations are not affected by the number of co-authors in a paper. Articles which are produced in collaboration attract more self-citations than articles produced by only one author. There is no statistically significant variation in citations counts (total and self-citations) in works that are result of different types of collaboration. A strong and statistically significant positive correlation exists between total citation count and frequency of self-citations. No relation could be ascertained between total citation count and proportion of self-citations. Authors tend to cite more of their recent works than the work of other authors. Total citation count and number of self-citations are positively correlated with the impact factor of source publication and correlation coefficient for total citations is much higher than that for self-citations. A negative correlation exhibits between impact factor and the share of self-citations. Of particular note is that the correlation in all the cases is of weak nature. Research limitations/implications – The research provides an understanding of the author self-citations in the field of LIS. readers are encouraged to further the study by taking into account large sample, tracing citations also from Book Citation Index (WoS) and comparing results with other allied subjects so as to validate the robustness of the findings of this study. Originality/value – Readers are encouraged to further the study by taking into account large sample, tracing citations also from Book Citation Index (WoS) and comparing results with other allied subjects so as to validate the robustness of the findings of this study.

Purpose – The purpose of this paper is to improve the conceptual-based search by incorporating structural ontological information such as concepts and relations. Generally, Semantic-based information retrieval aims to identify relevant information based on the meanings of the query terms or on the context of the terms and the performance of semantic information retrieval is carried out through standard measures-precision and recall. Higher precision leads to the (meaningful) relevant documents obtained and lower recall leads to the less coverage of the concepts. Design/methodology/approach – In this paper, the authors enhance the existing ontology-based indexing proposed by Kohler et al., by incorporating sibling information to the index. The index designed by Kohler et al., contains only super and sub-concepts from the ontology. In addition, in our approach, we focus on two tasks; query expansion and ranking of the expanded queries, to improve the efficiency of the ontology-based search. The aforementioned tasks make use of ontological concepts, and relations existing between those concepts so as to obtain semantically more relevant search results for a given query. Findings – The proposed ontology-based indexing technique is investigated by analysing the coverage of concepts that are being populated in the index. Here, we introduce a new measure called index enhancement measure, to estimate the coverage of ontological concepts being indexed. We have evaluated the ontology-based search for the tourism domain with the tourism documents and tourism-specific ontology. The comparison of search results based on the use of ontology “with and without query expansion” is examined to estimate the efficiency of the proposed query expansion task. The ranking is compared with the ORank system to evaluate the performance of our ontology-based search. From these analyses, the ontology-based search results shows better recall when compared to the other concept-based search systems. The mean average precision of the ontology-based search is found to be 0.79 and the recall is found to be 0.65, the ORank system has the mean average precision of 0.62 and the recall is found to be 0.51, while the concept-based search has the mean average precision of 0.56 and the recall is found to be 0.42. Practical implications – When the concept is not present in the domain-specific ontology, the concept cannot be indexed. When the given query term is not available in the ontology then the term-based results are retrieved. Originality/value – In addition to super and sub-concepts, we incorporate the concepts present in same level (siblings) to the ontological index. The structural information from the ontology is determined for the query expansion. The ranking of the documents depends on the type of the query (single concept query, multiple concept queries and concept with relation queries) and the ontological relations that exists in the query and the documents. With this ontological structural information, the search results showed us better coverage of concepts with respect to the query.