Search results

Product returns are a major challenge for e-businesses as they involve huge logistical and operational costs. Therefore, it becomes crucial to predict returns in advance. This study aims to evaluate different genres of classifiers for product return chance prediction, and further optimizes the best performing model.

An e-commerce data set having categorical type attributes has been used for this study. Feature selection based on chi-square provides a selective features-set which is used as inputs for model building. Predictive models are attempted using individual classifiers, ensemble models and deep neural networks. For performance evaluation, 75:25 train/test split and 10-fold cross-validation strategies are used. To improve the predictability of the best performing classifier, hyperparameter tuning is performed using different optimization methods such as, random search, grid search, Bayesian approach and evolutionary models (genetic algorithm, differential evolution and particle swarm optimization).

A comparison of F1-scores revealed that the Bayesian approach outperformed all other optimization approaches in terms of accuracy. The predictability of the Bayesian-optimized model is further compared with that of other classifiers using experimental analysis. The Bayesian-optimized XGBoost model possessed superior performance, with accuracies of 77.80% and 70.35% for holdout and 10-fold cross-validation methods, respectively.

Given the anonymized data, the effects of individual attributes on outcomes could not be investigated in detail. The Bayesian-optimized predictive model may be used in decision support systems, enabling real-time prediction of returns and the implementation of preventive measures.

There are very few reported studies on predicting the chance of order return in e-businesses. To the best of the authors’ knowledge, this study is the first to compare different optimization methods and classifiers, demonstrating the superiority of the Bayesian-optimized XGBoost classification model for returns prediction.

Aficionados of wine festivals, a component of wine tourism experience, engage in vigorous online discussions that influence fellow travelers’ purchase behaviors. This study aims to delve into these overlooked discussions, identifying emotions, topics and assessing their usefulness in TripAdvisor’s Travel Forums for two US wine festivals: Taste of Yountville and Epcot International Food and Wine Festival, located in traditional and nontraditional wine tourism destinations.

The study uses state-of-art sentiment analysis and topic modeling methods to extract emotions and underlying latent topics in travel forum discussions. Drawing from information theory, two regression analyses are performed on 10,677 forum posts to examine how the extracted Ekman’s emotions and key underlying topics influence the helpfulness of wine forum posts for each festival.

While three topics were identified in Epcot and four in Yountville, both festival platforms highlight travelers’ common preferences for “culinary experience” and “planning” attributes but reveal notable differences in their utility. Other shared novel findings include the importance of “anger” and “surprise” emotions on the helpfulness of forum posts.

These findings enhance wine festival managers’ and destination planners’ understanding of online travelers’ preferences and cognitive evaluation of user-generated contents’ usefulness. This marketing intelligence informs strategies for boosting the wine destination’s economic development.

This research offers a novel comparative analysis of social media on wine festival tourism experiences in diverse regions. Unlike hotel reviews, typically posted after consumption, forums offer unique and broader perspectives on discussions before, during, and after experiencing the wine festival.

In 2020, the IFRS Foundation’s public consultation on Sustainability Reporting provided an opportunity for stakeholders to share their opinions on the Foundation’s proposals. This paper aims to analyze the comment letters that would legitimize the IFRS Foundation to institutionalize the International Sustainability Standards Board (ISSB).

This study used Python to develop a model for analyzing all 577 submissions that the IFRS Foundation received, using a combination of quantitative and qualitative content analysis methods.

Support for the creation of the ISSB was not unanimous but reached 68%. Key supporting arguments were that the IFRS Foundation could harmonize sustainability reporting standards by leveraging its expertise in setting accounting standards, and use its existing relationships to enforce sustainability reporting. Key counterarguments were: the IFRS Foundation lacks expertise in the areas of sustainability and climate; sustainability reporting should be integrated into financial reporting rather than being disclosed separately; the proposals were limited in scope (single materiality, focus on investors’ information needs and climate change centrism); and the IFRS Foundation should aim to endorse already established frameworks instead.

A consensus between supporters and critics was the need to make sustainability reporting mandatory. Endorsed by IOSCO, the ISSB released its inaugural standards, focusing on climate-related disclosures, effective from 2024 in jurisdictions that choose to adopt them.

The findings show that the establishment of the ISSB by the IFRS Foundation only partially fulfilled the demand for the harmonization of sustainability reporting standards. As a result, broader and non-investor-centric sustainability information may continue to be reported under alternative frameworks.

This study aims to analyse and understand customer sentiments and perceptions from neobanking mobile applications by using advanced machine learning and text mining techniques.

This study explores a substantial large data set of 330,399 user reviews available in the form of unstructured textual data from neobanking mobile applications. This study is aimed to extract meaningful patterns, topics, sentiments and themes from the data.

The results show that the success of neobanking mobile applications depends on user experience, security features, personalised services and technological innovation.

This study is limited to textual resources available in the public domain, and hence may not present the entire range of user experiences. Further studies should incorporate a wider range of data sources and investigate the impact of regional disparities on user preferences.

This study provides actionable ideas for neobanking service providers, enabling them to improve service quality and mobile application user experience by integrating customer input and the latest trends. These results can offer important inputs to the process of user interaction design, implementation of new features and customer support services.

This study uses text mining approaches to analyse neobanking mobile applications, which further contribute to the growing literature on digital banking and FinTech. This study offers a unique view of consumer behaviour and preferences in the realm of digital banking, which will add to the literature on the quality of service concerning mobile applications.

This study explored whether women could “have it all,” both at home and in the workplace. Using neoliberal feminism, mental load theory and intergenerational perspective as theoretical frameworks, this study explored how neoliberal ideologies which emphasized individual agency, economic empowerment and self-responsibility interact with persistent gendered expectations/norms to influence women’s experiences in navigating familial commitments and career aspirations.

Around 140 (N = 140) women living in Australia were recruited to participate in a qualitative, open-ended questionnaire that aimed to explore their: (1) perceptions and (2) expectations about (a) how gender roles evolved for them from youth to adulthood in various contexts, (b) how their family structures and dynamics, such as attitudes toward marriage, caregiving and/or household responsibilities, have changed and (c) what has/have influenced their career aspirations and family choices.

Results revealed a trend of women who worked hard at home and professionally. Unlike women who in the past lived more traditional lives, women in our cohort focused on their career as an important part of their identity and self-fulfillment. However, many women did report heightened mental load, stress and a lack of physical exercise in their daily lives.

This study revealed complex interplay between societal norms, intergenerational influences and the cognitive burdens associated with managing multiple roles. By examining these dynamics and using an integrated theoretical framework, the article aimed to holistically explain the challenges women in Australia encounter as they try to balance familial obligations with career ambitions within changing socioeconomic contexts.

This study investigates consumer perspectives on cultural appropriation in the fashion industry by analysing user-generated content on Douyin.

Using text-mining techniques, including topic modeling and sentiment analysis, 6,584 comments related to the Dior midi-length skirt controversy were analyzed to identify key themes and sentiments.

The study reveals that cultural appropriation elicits polarized responses. Positive themes, such as cultural appreciation, innovation and global exposure, highlight consumer approval of respectful and creative integration of cultural elements. Negative themes, including cultural theft, historical inaccuracy and commercial exploitation, underscore concerns about commodification and misuse of cultural symbols.

Fashion brands should prioritize cultural sensitivity by collaborating with cultural communities, ensuring historical accuracy and promoting ethical engagement with cultural symbols. Proactively addressing these issues through real-time consumer feedback can help mitigate backlash, foster trust and enhance brand equity.

This study advances the discourse on cultural appropriation by leveraging real-time user-generated content to provide actionable insights for ethical practices in the fashion industry.

This study aims to explore the relationship between wine label content and consumer reviews on Vivino, focusing on how label information compares to consumer perceptions and purchase decisions.

The research uses text mining, image mining and topic modeling techniques to analyze a data set of 444 highly rated Portuguese wines and 993,945 consumer reviews from Vivino. It examines the overlap between topics discussed in consumer reviews and the information provided on wine labels.

The findings reveal that wine labels have a limited similarity with consumer reviews. While consumer reviews primarily emphasize sensory characteristics like fruitiness and tannins, wine labels focus more on descriptive and technical information.

This research provides new insights into the dynamic relationship between wine labeling and consumer behavior. By analyzing the alignment between traditional wine labels and online consumer reviews, the study offers valuable implications for wineries seeking to optimize label design to match consumer preferences, particularly sensory attributes better. This study extends existing research and highlights critical gaps in how wine labels convey essential sensory information to consumers.

The study examines the characteristics and development trends of female entrepreneurship publications, cooperation networks between countries, journals and individuals, intellectual structure of female entrepreneurship studies in Africa and hot research topics. Future comparative studies in different contexts and interdisciplinary collaboration can enrich the understanding about female entrepreneurship research.

The authors used text mining to analyze 130 peer-reviewed articles published from 1975 to 2022 for keywords and classify them into eight main classes: (1) Paradoxical space and informality, (2) work–family conflict, (3) women's entrepreneurial identity and networking, (4) rural women's entrepreneurial activities in the agricultural sector, (5) religious belief and women's entrepreneurial practice, (6) financial trap and environmental challenges, (7) women's entrepreneurial intentions and capacity building and (8) women in cultural entrepreneurship.

Female entrepreneurship publications develop significantly. Since 1975, African female entrepreneurship study has grown. Results show 130 publications from 1975 to 2023, with two papers published yearly in 2006–2011 and 23 in 2023, indicating growing interest. Paradoxical space and informality, work–family conflict, women's entrepreneurial identity and networking, religious belief and practice, financial trap and environmental challenges and entrepreneurial intentions and capacity building were hot topics identified by topic modeling analysis.

Female entrepreneurs have looser intellectual networks. Nation, organization and researcher communication is inadequate. Collaborating researchers from different universities and countries may develop the field.

This study is more data-driven and less biased than earlier reviews because it is based on thousands of citation data rather than a small number of papers pre-selected by the researchers. Displaying the field's structure and evolution enhances previous reviews.

This study aims to elucidate the dynamics of social media discourse during global health events, specifically investigating how users across different platforms perceive, react to and engage with information concerning such crises.

A mixed-method approach was employed, combining both quantitative and qualitative data collection. Initially, thematic analysis was applied to a data set of social media posts across four major platforms over a 12-month period. This was followed by sentiment analysis to discern the predominant emotions embedded within these communications. Statistical tools were used to validate findings, ensuring robustness in the results.

The results showcased discernible thematic and emotional disparities across platforms. While some platforms leaned toward factual information dissemination, others were rife with user sentiments, anecdotes and personal experiences. Overall, a global sense of concern was evident, but the ways in which this concern manifested varied significantly between platforms.

The primary limitation is the potential non-representativeness of the sample, as only four major social media platforms were considered. Future studies might expand the scope to include emerging platforms or non-English language platforms. Additionally, the rapidly evolving nature of social media discourse implies that findings might be time-bound, necessitating periodic follow-up studies.

Understanding the nature of discourse on various platforms can guide health organizations, policymakers and communicators in tailoring their messages. Recognizing where factual information is required, versus where sentiment and personal stories resonate, can enhance the efficacy of public health communication strategies.

The study underscores the societal reliance on social media for information during crises. Recognizing the different ways in which communities engage with, and are influenced by, platform-specific discourse can help in fostering a more informed and empathetic society, better equipped to handle global challenges.

This research is among the first to offer a comprehensive, cross-platform analysis of social media discourse during a global health event. By comparing user engagement across platforms, it provides unique insights into the multifaceted nature of public sentiment and information dissemination during crises.

This study aims to investigate the digital entrepreneurial intentions of Albanian youth, identify the obstacles they face in starting digital businesses and examine their preferences regarding the types of businesses they aspire to establish. The Theory of Planned Behavior (TPB) is used as a framework to analyze these factors.

Primary data were collected via questionnaires distributed in public and private universities. In a sample of 325 students, Structural Equation Modeling with Confirmatory Factor Analysis, path analysis and machine learning-based text analysis were used.

This study reveals significant impacts of innovativeness, attitude towards entrepreneurship, subjective norms, perceived behavioral control and self-efficacy on digital entrepreneurial intentions among Albanian students. Additionally, text mining highlights a strong preference for digital entrepreneurship.

The theoretical contributions of this study include applying Structural Equation Modeling to reveal insights into the impact of entrepreneurial factors and obstacles. The findings can inform policymakers and educators in designing targeted interventions to support student entrepreneurship. Meanwhile, the limitations of this study encompass a small sample size, lack of time series and panel data and the absence of an evaluation of the impact of education system practices, along with the need to investigate the effects of young population emigration from Albania to the EU.

This research contributes to the understanding of digital entrepreneurial intentions and behavior by using TPB in the Albanian context, offering access to a diverse dataset from Albanian universities, testing the direct impact of innovativeness on entrepreneurial behavior and pioneering the use of machine learning techniques for text analysis. Thus, it provides novel insights into the entrepreneurial landscape in Albania. In addition, this work can drive initiatives to support student entrepreneurship and bridge the gap between academia and industry in Albania.