The advent of 3D virtual presentation technology for clothing has led to the gradual popularisation of digital virtual clothing in the modern fashion industry. However, there remains a gap between the application of this technology and the integration of cultural attributes in the field of digital communication of traditional cultural clothing. Consequently, the objective of this paper is to propose the establishment of a fusion system integrating archaeological research on traditional culture with emerging virtual presentation technology. This paper draws inspiration from the replicability and easy dissemination of digital products to combine cultural archaeology and digital technology. The aim is to provide ideas for the diversity of dissemination of cultural heritage. The research object is Diplomatic Envoys, a Chinese mural painting of the Tang Dynasty that depicts friendly exchanges between countries. The research is divided into two research stages. A CLO3D software-based digital restoration test was conducted to reproduce the costumes of officials and foreign envoys depicted in the Tang Dynasty mural. The FAHP model was employed to verify the accuracy of the restoration results. The experiment demonstrated that the digitally reconstructed clothing exhibited a high degree of similarity to the unearthed mural figure clothing object. Furthermore, the restoration result passed the credibility verification, resulting in a ‘credible’ outcome. The application of digital virtual simulation clothing restoration methods offers two key advantages. Firstly, in comparison with traditional clothing restoration methods, digital restoration enables the rapid assessment of the resulting clothing effect, thereby reducing the likelihood of secondary damage to cultural relics due to manual errors. Secondly, the benefits of digital technology facilitate the convenient storage, replication, and dissemination of clothing data information. Data can not only be extended to online exhibition halls but also to game animation, clothing production, and other fields for the purposes of creative redesign and information dissemination. Furthermore, these benefits can penetrate the education industry to disseminate information to the public through all-round display models and explanations.
{"title":"Digital Virtual Simulation for Cultural Clothing Restoration: Case Study of Tang Dynasty Mural ‘Diplomatic Envoys’ from Crown Prince Zhang Huai’s Tomb","authors":"Chunxiao Liu, RongRong Cui, Zhicheng Wang","doi":"10.3390/jtaer19020069","DOIUrl":"https://doi.org/10.3390/jtaer19020069","url":null,"abstract":"The advent of 3D virtual presentation technology for clothing has led to the gradual popularisation of digital virtual clothing in the modern fashion industry. However, there remains a gap between the application of this technology and the integration of cultural attributes in the field of digital communication of traditional cultural clothing. Consequently, the objective of this paper is to propose the establishment of a fusion system integrating archaeological research on traditional culture with emerging virtual presentation technology. This paper draws inspiration from the replicability and easy dissemination of digital products to combine cultural archaeology and digital technology. The aim is to provide ideas for the diversity of dissemination of cultural heritage. The research object is Diplomatic Envoys, a Chinese mural painting of the Tang Dynasty that depicts friendly exchanges between countries. The research is divided into two research stages. A CLO3D software-based digital restoration test was conducted to reproduce the costumes of officials and foreign envoys depicted in the Tang Dynasty mural. The FAHP model was employed to verify the accuracy of the restoration results. The experiment demonstrated that the digitally reconstructed clothing exhibited a high degree of similarity to the unearthed mural figure clothing object. Furthermore, the restoration result passed the credibility verification, resulting in a ‘credible’ outcome. The application of digital virtual simulation clothing restoration methods offers two key advantages. Firstly, in comparison with traditional clothing restoration methods, digital restoration enables the rapid assessment of the resulting clothing effect, thereby reducing the likelihood of secondary damage to cultural relics due to manual errors. Secondly, the benefits of digital technology facilitate the convenient storage, replication, and dissemination of clothing data information. Data can not only be extended to online exhibition halls but also to game animation, clothing production, and other fields for the purposes of creative redesign and information dissemination. Furthermore, these benefits can penetrate the education industry to disseminate information to the public through all-round display models and explanations.","PeriodicalId":46198,"journal":{"name":"Journal of Theoretical and Applied Electronic Commerce Research","volume":"30 1","pages":""},"PeriodicalIF":5.6,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141258614","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
To decrease privacy risks, consumers may choose to misrepresent themselves when they are asked to offer personal information. Using a game theoretic model, this study examines the impact of consumer misrepresentation on both a monopolistic firm and consumers. The results show that consumer misrepresentation may benefit the firm, but hurt consumers under certain conditions. In addition, we find that when the unit cost of personalized service is low, consumer misrepresentation may encourage the firm to provide a higher personalized service level. Moreover, when consumers misrepresent themselves and the firm only covers part of the market, a greater unit value of consumer private information will reduce the firm’s profit, while a greater unit cost of personalized service will increase the firm’s profit. The analysis reported here provides important insights regarding the application of consumer information in online personalized marketing and consumer privacy protection.
{"title":"Information Collection and Personalized Service Strategy of Monopoly under Consumer Misrepresentation","authors":"Mingyue Zhong, Yan Cheng, Shu-e Mei, Weijun Zhong","doi":"10.3390/jtaer19020067","DOIUrl":"https://doi.org/10.3390/jtaer19020067","url":null,"abstract":"To decrease privacy risks, consumers may choose to misrepresent themselves when they are asked to offer personal information. Using a game theoretic model, this study examines the impact of consumer misrepresentation on both a monopolistic firm and consumers. The results show that consumer misrepresentation may benefit the firm, but hurt consumers under certain conditions. In addition, we find that when the unit cost of personalized service is low, consumer misrepresentation may encourage the firm to provide a higher personalized service level. Moreover, when consumers misrepresent themselves and the firm only covers part of the market, a greater unit value of consumer private information will reduce the firm’s profit, while a greater unit cost of personalized service will increase the firm’s profit. The analysis reported here provides important insights regarding the application of consumer information in online personalized marketing and consumer privacy protection.","PeriodicalId":46198,"journal":{"name":"Journal of Theoretical and Applied Electronic Commerce Research","volume":"42 1","pages":""},"PeriodicalIF":5.6,"publicationDate":"2024-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141196950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
To reduce the losses caused by insufficient preservation efforts during transportation, the preservation effort level has been the focus of research. In the fierce competition of online sales, it is particularly important to reduce the cost of damaged goods by improving the level of preservation efforts. Therefore, according to Stackelberg game theory, this article establishes five decision-making models and incorporates the damage rate and preservation effort level into the research. Finally, this article coordinates the online shipping supply chain (SC) through a joint contract. After comparing and analyzing the model results, research has found that: (1) in centralized model, the level of preservation effort reaches its optimal level and the system benefit is maximized; (2) under third-party logistics (TPL) leading decision-making, the different bearers of cargo damage costs will not affect the profits of both parties and the system; (3) among the four decentralized models, the level of preservation efforts and system profit are highest when the decision is led by online store and TPL bears the cost of damaged goods; and (4) under a given sharing ratio, when the logistics service quotation satisfies a certain range of condition, the online shopping SC can achieve Pareto improvement. This paper studies the differences and reasons for decision models in the supply and demand relationship between online stores and TPL, which provides fresh product e-commerce decision-makers with a theoretical basis.
{"title":"Coordination of Online Shopping Supply Chain Considering Fresh Product Preservation Efforts and Cargo Damage Costs","authors":"Haiping Ren, Yingxin Hu","doi":"10.3390/jtaer19020068","DOIUrl":"https://doi.org/10.3390/jtaer19020068","url":null,"abstract":"To reduce the losses caused by insufficient preservation efforts during transportation, the preservation effort level has been the focus of research. In the fierce competition of online sales, it is particularly important to reduce the cost of damaged goods by improving the level of preservation efforts. Therefore, according to Stackelberg game theory, this article establishes five decision-making models and incorporates the damage rate and preservation effort level into the research. Finally, this article coordinates the online shipping supply chain (SC) through a joint contract. After comparing and analyzing the model results, research has found that: (1) in centralized model, the level of preservation effort reaches its optimal level and the system benefit is maximized; (2) under third-party logistics (TPL) leading decision-making, the different bearers of cargo damage costs will not affect the profits of both parties and the system; (3) among the four decentralized models, the level of preservation efforts and system profit are highest when the decision is led by online store and TPL bears the cost of damaged goods; and (4) under a given sharing ratio, when the logistics service quotation satisfies a certain range of condition, the online shopping SC can achieve Pareto improvement. This paper studies the differences and reasons for decision models in the supply and demand relationship between online stores and TPL, which provides fresh product e-commerce decision-makers with a theoretical basis.","PeriodicalId":46198,"journal":{"name":"Journal of Theoretical and Applied Electronic Commerce Research","volume":"49 1","pages":""},"PeriodicalIF":5.6,"publicationDate":"2024-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141196954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The prediction of bankruptcy risk poses a formidable challenge in the fields of economics and finance, particularly within the healthcare industry, where it carries significant economic implications. The burgeoning field of healthcare electronic commerce, continuously evolving through technological advancements and changing regulations, introduces additional layers of complexity. We collected financial data from 1265 U.S. healthcare industries to predict bankruptcy based on 40 financial ratios using multi-class classification machine learning models across various industry subsectors and market capitalizations. The exceptionally high post-tuning accuracy rates, exceeding 90%, along with high-performance metrics solidified the robustness and exceptional predictive capability of the gradient boosting model in bankruptcy prediction. The results also demonstrate the power and sensitivity of financial ratios in predicting bankruptcy based on financial ratios. The Altman models highlight the return on investment (ROI) as the most important parameter for predicting bankruptcy risk in healthcare industries. The Ohlson model identifies return on assets (ROA) as an important ratio specifically for predicting bankruptcy risk within industry subsectors. Furthermore, it underscores the significance of both ROA and the enterprise value to earnings before interest and taxes (EV/EBIT) ratios as important parameters for predicting bankruptcy based on market capitalization. Recognizing these ratios enables proactive decision making that enhances resilience. Our findings contribute to informed risk management strategies, allowing for better management of healthcare industries in crises like those experienced in 2022 and even on a global scale.
{"title":"Risk Analysis of Bankruptcy in the U.S. Healthcare Industries Based on Financial Ratios: A Machine Learning Analysis","authors":"Hadi Gholampoor, Majid Asadi","doi":"10.3390/jtaer19020066","DOIUrl":"https://doi.org/10.3390/jtaer19020066","url":null,"abstract":"The prediction of bankruptcy risk poses a formidable challenge in the fields of economics and finance, particularly within the healthcare industry, where it carries significant economic implications. The burgeoning field of healthcare electronic commerce, continuously evolving through technological advancements and changing regulations, introduces additional layers of complexity. We collected financial data from 1265 U.S. healthcare industries to predict bankruptcy based on 40 financial ratios using multi-class classification machine learning models across various industry subsectors and market capitalizations. The exceptionally high post-tuning accuracy rates, exceeding 90%, along with high-performance metrics solidified the robustness and exceptional predictive capability of the gradient boosting model in bankruptcy prediction. The results also demonstrate the power and sensitivity of financial ratios in predicting bankruptcy based on financial ratios. The Altman models highlight the return on investment (ROI) as the most important parameter for predicting bankruptcy risk in healthcare industries. The Ohlson model identifies return on assets (ROA) as an important ratio specifically for predicting bankruptcy risk within industry subsectors. Furthermore, it underscores the significance of both ROA and the enterprise value to earnings before interest and taxes (EV/EBIT) ratios as important parameters for predicting bankruptcy based on market capitalization. Recognizing these ratios enables proactive decision making that enhances resilience. Our findings contribute to informed risk management strategies, allowing for better management of healthcare industries in crises like those experienced in 2022 and even on a global scale.","PeriodicalId":46198,"journal":{"name":"Journal of Theoretical and Applied Electronic Commerce Research","volume":"37 1","pages":""},"PeriodicalIF":5.6,"publicationDate":"2024-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141196812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Online reviews have become an important source of information for consumers, significantly influencing their purchasing decisions. However, the abundance and variety of review formats, especially the mix of text, image, and video elements, can lead to information overload and hinder effective decision-making. This study investigates how different review formats and their combinations affect the perceived helpfulness of reviews. We develop a comprehensive framework to analyze the interactions between text, image, and video elements and their impact on the helpfulness of reviews. We collect and code 8693 online reviews from JingDong Mall Mallacross six product categories, including both experience products and search products, and use multiple regression analysis to test our hypotheses. Our results show that textual review elements significantly increase review helpfulness. However, their effectiveness decreases as the amount of information increases, indicating cognitive overload. Text reviews are more prone to contribute to information overload, while visual elements such as images and videos generally do not contribute to information overload in the coexistence of text, image, and video reviews. Imagery components have a minimal effect on review helpfulness. Video elements are relatively short, which may not be sufficient to convey useful information. We also find that the impact of review formats varies between experience products and search products, and that star ratings moderate the alignment of textual or imagery components with consumer expectations. We conclude that the hybrid of text, image, and video elements in online reviews plays a crucial role in shaping consumer decision-making and information overload. Our research contributes to the literature on online reviews and information overload while providing practical implications for online retailers, review platforms, and consumers to optimize review formats, star ratings, and product types to facilitate informed purchase decisions.
{"title":"Online Review Helpfulness and Information Overload: The Roles of Text, Image, and Video Elements","authors":"Liang Wang, Gaofeng Che, Jiantuan Hu, Lin Chen","doi":"10.3390/jtaer19020064","DOIUrl":"https://doi.org/10.3390/jtaer19020064","url":null,"abstract":"Online reviews have become an important source of information for consumers, significantly influencing their purchasing decisions. However, the abundance and variety of review formats, especially the mix of text, image, and video elements, can lead to information overload and hinder effective decision-making. This study investigates how different review formats and their combinations affect the perceived helpfulness of reviews. We develop a comprehensive framework to analyze the interactions between text, image, and video elements and their impact on the helpfulness of reviews. We collect and code 8693 online reviews from JingDong Mall Mallacross six product categories, including both experience products and search products, and use multiple regression analysis to test our hypotheses. Our results show that textual review elements significantly increase review helpfulness. However, their effectiveness decreases as the amount of information increases, indicating cognitive overload. Text reviews are more prone to contribute to information overload, while visual elements such as images and videos generally do not contribute to information overload in the coexistence of text, image, and video reviews. Imagery components have a minimal effect on review helpfulness. Video elements are relatively short, which may not be sufficient to convey useful information. We also find that the impact of review formats varies between experience products and search products, and that star ratings moderate the alignment of textual or imagery components with consumer expectations. We conclude that the hybrid of text, image, and video elements in online reviews plays a crucial role in shaping consumer decision-making and information overload. Our research contributes to the literature on online reviews and information overload while providing practical implications for online retailers, review platforms, and consumers to optimize review formats, star ratings, and product types to facilitate informed purchase decisions.","PeriodicalId":46198,"journal":{"name":"Journal of Theoretical and Applied Electronic Commerce Research","volume":"43 1","pages":""},"PeriodicalIF":5.6,"publicationDate":"2024-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141196811","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Wen Cheng, Qunqi Wu, Qian Li, Fei Ye, Lingling Tan
In light of increasingly prominent environmental issues, inspiring green supply chain (GSC) members to engage in collaborative innovation is crucial to improve environmental performance. In this paper, in relation to a two-level GSC consisting of manufacturers and suppliers, differential equations involving the greenness of intermediate and final products as state variables are constructed considering the effect of digital capability on green innovation. Subsequently, designs for three incentive mechanisms—the greenness reward, the R&D effort reward, and the digital construction reward—are presented, and their long-term dynamic effects on the economic, environmental, and social benefits are compared and analyzed. Finally, the impacts of consumer green preference and the contribution of digital capability to the advancement of green innovation are explored. The findings show that all these incentives can boost economic, environmental, and social benefits while motivating the supplier. To achieve the best incentive effect, the reward coefficient should fall within a specific range. The digital construction reward mechanism is the most favourable in the initial stage, while the R&D effort reward mechanism is the most appropriate in the long term. The promotion effects of digital capability on green innovation and consumer green preference have the potential to enhance economic, environmental, and social performance.
{"title":"Dynamic Incentive Mechanisms for Collaborative Innovation of Green Supply Chain Considering Digital Capability and Consumer Green Preference","authors":"Wen Cheng, Qunqi Wu, Qian Li, Fei Ye, Lingling Tan","doi":"10.3390/jtaer19020065","DOIUrl":"https://doi.org/10.3390/jtaer19020065","url":null,"abstract":"In light of increasingly prominent environmental issues, inspiring green supply chain (GSC) members to engage in collaborative innovation is crucial to improve environmental performance. In this paper, in relation to a two-level GSC consisting of manufacturers and suppliers, differential equations involving the greenness of intermediate and final products as state variables are constructed considering the effect of digital capability on green innovation. Subsequently, designs for three incentive mechanisms—the greenness reward, the R&D effort reward, and the digital construction reward—are presented, and their long-term dynamic effects on the economic, environmental, and social benefits are compared and analyzed. Finally, the impacts of consumer green preference and the contribution of digital capability to the advancement of green innovation are explored. The findings show that all these incentives can boost economic, environmental, and social benefits while motivating the supplier. To achieve the best incentive effect, the reward coefficient should fall within a specific range. The digital construction reward mechanism is the most favourable in the initial stage, while the R&D effort reward mechanism is the most appropriate in the long term. The promotion effects of digital capability on green innovation and consumer green preference have the potential to enhance economic, environmental, and social performance.","PeriodicalId":46198,"journal":{"name":"Journal of Theoretical and Applied Electronic Commerce Research","volume":"122 1","pages":""},"PeriodicalIF":5.6,"publicationDate":"2024-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141197209","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This research investigates the effects of “choose-one-over-another” monopolistic strategies on two-sided platforms, analyzing the implications of such practices on network effects and platform economics through the Hotelling model. Our key findings include the following: (1) “Choose-one-over-another” policies enhance positive network effects, increasing multi-homing on the demand side but reducing overall platform revenue. These policies also intensify negative network effects, leading to higher prices for supply-side users and thereby undermining the welfare of demand-side users. (2) After antitrust interventions, platforms adjust pricing dynamically, increasing for one side and decreasing for the other in response to changes in same-side network effects, which in turn influences multi-homing behaviors and revenue impacts differently before and after the enforcement of such policies. (3) Without exclusive selection mandates, platform pricing strategies tend to lower prices for supply-side users, especially under competitive pressures or weaker positive network effects, potentially increasing platform revenue and overall supply chain welfare under certain conditions. This study highlights the critical role of regulatory oversight in curbing monopolistic platform behaviors to protect user rights and ensure market health, offering strategic guidance for platform management amidst competitive and operational challenges.
{"title":"Impact of Exclusive Choice Policies on Platform Supply Chains: When Both Same-Side and Cross-Side Network Effects Exist","authors":"Haijun Chen, Qi Xu","doi":"10.3390/jtaer19020061","DOIUrl":"https://doi.org/10.3390/jtaer19020061","url":null,"abstract":"This research investigates the effects of “choose-one-over-another” monopolistic strategies on two-sided platforms, analyzing the implications of such practices on network effects and platform economics through the Hotelling model. Our key findings include the following: (1) “Choose-one-over-another” policies enhance positive network effects, increasing multi-homing on the demand side but reducing overall platform revenue. These policies also intensify negative network effects, leading to higher prices for supply-side users and thereby undermining the welfare of demand-side users. (2) After antitrust interventions, platforms adjust pricing dynamically, increasing for one side and decreasing for the other in response to changes in same-side network effects, which in turn influences multi-homing behaviors and revenue impacts differently before and after the enforcement of such policies. (3) Without exclusive selection mandates, platform pricing strategies tend to lower prices for supply-side users, especially under competitive pressures or weaker positive network effects, potentially increasing platform revenue and overall supply chain welfare under certain conditions. This study highlights the critical role of regulatory oversight in curbing monopolistic platform behaviors to protect user rights and ensure market health, offering strategic guidance for platform management amidst competitive and operational challenges.","PeriodicalId":46198,"journal":{"name":"Journal of Theoretical and Applied Electronic Commerce Research","volume":"48 1","pages":""},"PeriodicalIF":5.6,"publicationDate":"2024-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141151368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Textual emotion recognition (TER) has significant commercial potential since it can be used as an excellent tool to monitor a brand/business reputation, understand customer satisfaction, and personalize recommendations. It is considered a natural language processing task that can be used to understand and classify emotions such as anger, happiness, and surprise being conveyed in a piece of text (product reviews, tweets, and comments). Despite the advanced development of deep learning and particularly transformer architectures, Arabic-focused models for emotion classification have not achieved satisfactory accuracy. This is mainly due to the morphological richness, agglutination, dialectal variation, and low-resource datasets of the Arabic language, as well as the unique features of user-generated text such as noisiness, shortness, and informal language. This study aims to illustrate the effectiveness of large language models on Arabic multi-label emotion classification. We evaluated GPT-3.5 Turbo and GPT-4 using three different settings: in-context learning, emotional stimuli prompt, and fine-tuning. The ultimate objective of this research paper is to determine if these LLMs, which have multilingual capabilities, could contribute to enhancing the aforementioned task and encourage its use within the context of an e-commerce environment for example. The experimental results indicated that the fine-tuned GPT-3.5 Turbo model achieved an accuracy of 62.03%, a micro-averaged F1-score of 73%, and a macro-averaged F1-score of 62%, establishing a new state-of-the-art benchmark for the task of Arabic multi-label emotion recognition.
文本情感识别（TER）具有巨大的商业潜力，因为它可以作为监测品牌/企业声誉、了解客户满意度和个性化推荐的绝佳工具。它被认为是一种自然语言处理任务，可用于理解和分类文本（产品评论、推特和评论）中传达的愤怒、快乐和惊讶等情绪。尽管深度学习，尤其是转换器架构的发展非常迅速，但以阿拉伯语为重点的情感分类模型并未达到令人满意的准确度。这主要是由于阿拉伯语的形态丰富性、聚合性、方言差异和低资源数据集，以及用户生成文本的独特特征，如噪音、短小和非正式语言。本研究旨在说明大型语言模型在阿拉伯语多标签情感分类中的有效性。我们使用三种不同的设置对 GPT-3.5 Turbo 和 GPT-4 进行了评估：上下文学习、情感刺激提示和微调。本研究论文的最终目的是确定这些具有多语言功能的 LLM 是否有助于增强上述任务，并鼓励在电子商务环境等背景下使用这些 LLM。实验结果表明，经过微调的 GPT-3.5 Turbo 模型的准确率达到了 62.03%，微观平均 F1 分数为 73%，宏观平均 F1 分数为 62%，为阿拉伯语多标签情感识别任务建立了一个新的先进基准。
{"title":"Evaluating Arabic Emotion Recognition Task Using ChatGPT Models: A Comparative Analysis between Emotional Stimuli Prompt, Fine-Tuning, and In-Context Learning","authors":"El Habib Nfaoui, Hanane Elfaik","doi":"10.3390/jtaer19020058","DOIUrl":"https://doi.org/10.3390/jtaer19020058","url":null,"abstract":"Textual emotion recognition (TER) has significant commercial potential since it can be used as an excellent tool to monitor a brand/business reputation, understand customer satisfaction, and personalize recommendations. It is considered a natural language processing task that can be used to understand and classify emotions such as anger, happiness, and surprise being conveyed in a piece of text (product reviews, tweets, and comments). Despite the advanced development of deep learning and particularly transformer architectures, Arabic-focused models for emotion classification have not achieved satisfactory accuracy. This is mainly due to the morphological richness, agglutination, dialectal variation, and low-resource datasets of the Arabic language, as well as the unique features of user-generated text such as noisiness, shortness, and informal language. This study aims to illustrate the effectiveness of large language models on Arabic multi-label emotion classification. We evaluated GPT-3.5 Turbo and GPT-4 using three different settings: in-context learning, emotional stimuli prompt, and fine-tuning. The ultimate objective of this research paper is to determine if these LLMs, which have multilingual capabilities, could contribute to enhancing the aforementioned task and encourage its use within the context of an e-commerce environment for example. The experimental results indicated that the fine-tuned GPT-3.5 Turbo model achieved an accuracy of 62.03%, a micro-averaged F1-score of 73%, and a macro-averaged F1-score of 62%, establishing a new state-of-the-art benchmark for the task of Arabic multi-label emotion recognition.","PeriodicalId":46198,"journal":{"name":"Journal of Theoretical and Applied Electronic Commerce Research","volume":"35 1","pages":""},"PeriodicalIF":5.6,"publicationDate":"2024-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140932066","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Eye tracking plays a crucial role in consumer research. The aim of this work is to present the statuses of studies that used eye tracking as an instrument in consumer research to investigate food from a marketing perspective. For this purpose, a bibliometric review of 118 articles from the Business Source Premier and Web of Science Core Collection database was compiled. The bibliometric review provides information on publication trends, leading authors, collaborative networks, journals, institutions, countries, articles, keywords, and themes investigated. Publications in the research field have appeared since 2011, primarily in Europe, the United States, and Uruguay. Three areas of research streams were identified: (1) how consumers became aware of and chose food, (2) nutritional information and its impact, and (3) how food information and its visual attention led to certain consumer behavior. The bibliographic review summarized past research directions and, thus, identified possibilities for future research streams.
眼动仪在消费者研究中起着至关重要的作用。这项工作的目的是介绍在消费者研究中使用眼动仪从营销角度调查食品的研究现状。为此，我们对 Business Source Premier 和 Web of Science Core Collection 数据库中的 118 篇文章进行了文献计量审查。文献计量综述提供了有关出版趋势、主要作者、合作网络、期刊、机构、国家、文章、关键词和调查主题的信息。自 2011 年以来，该研究领域的出版物主要出现在欧洲、美国和乌拉圭。确定了三个研究领域：(1) 消费者如何认识和选择食品，(2) 营养信息及其影响，(3) 食品信息及其视觉注意力如何导致某些消费行为。文献综述总结了过去的研究方向，从而确定了未来研究方向的可能性。
{"title":"Eye Tracking as an Instrument in Consumer Research to Investigate Food from A Marketing Perspective: A Bibliometric and Visual Analysis","authors":"Tonia Ruppenthal, Nils Schweers","doi":"10.3390/jtaer19020057","DOIUrl":"https://doi.org/10.3390/jtaer19020057","url":null,"abstract":"Eye tracking plays a crucial role in consumer research. The aim of this work is to present the statuses of studies that used eye tracking as an instrument in consumer research to investigate food from a marketing perspective. For this purpose, a bibliometric review of 118 articles from the Business Source Premier and Web of Science Core Collection database was compiled. The bibliometric review provides information on publication trends, leading authors, collaborative networks, journals, institutions, countries, articles, keywords, and themes investigated. Publications in the research field have appeared since 2011, primarily in Europe, the United States, and Uruguay. Three areas of research streams were identified: (1) how consumers became aware of and chose food, (2) nutritional information and its impact, and (3) how food information and its visual attention led to certain consumer behavior. The bibliographic review summarized past research directions and, thus, identified possibilities for future research streams.","PeriodicalId":46198,"journal":{"name":"Journal of Theoretical and Applied Electronic Commerce Research","volume":"8 1","pages":""},"PeriodicalIF":5.6,"publicationDate":"2024-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140932124","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Consumers often rely on evaluations such as online reviews shared by other consumers when making purchasing decisions. Online reviews have emerged as a crucial marketing tool that offers a distinct advantage over traditional methods by fostering trust among consumers. Previous studies have identified group similarity between consumers and reviewers as a key variable with a potential impact on consumer responses and purchase intention. However, the results remain inconclusive. In this study, we identify self-construal and group similarity as key factors in the influence of online review ratings on consumers’ purchase intentions. We further investigate the role of consumers’ self-construal in shaping consumers’ perceptions of online reviews in terms of belongingness and diagnosticity. To test the hypothesis, we conducted a 2 (online review rating) × 2 (group similarity) × 2 (self-construal) ANOVA on 276 subjects collected through Amazon Mechanical Turk (MTurk), and contrast analysis and PROCESS macro model 12 were used for the interaction effect analysis and moderated mediation analysis. Our findings reveal that consumers with an interdependent self-construal are sensitive to both review ratings and group similarity with regards to their purchase intentions. They demonstrate a positive purchase intention when both group similarity and online review ratings are high. However, their purchase intention is not influenced by review ratings when group similarity is low. Conversely, consumers with an independent self-construal exhibit a more positive purchase intention when the online review rating is high, irrespective of group similarity. Additionally, our study highlights the mediating roles of perceived diagnosticity and belongingness in the relationship between online review ratings, group similarity, self-construal, and purchase intentions. Results show significant indirect effects for perceived diagnosticity and belongingness, meaning that the impact of online review ratings on purchase intention is mediated by these two variables. The outcomes of our research offer theoretical and practical implications concerning online reviews and suggest new avenues for future research in the area of online consumer behavior.
消费者在做出购买决定时，往往依赖于其他消费者分享的在线评论等评价。在线评论已成为一种重要的营销工具，与传统方法相比，它通过增进消费者之间的信任而具有明显优势。以往的研究发现，消费者与评论者之间的群体相似性是一个关键变量，可能对消费者的反应和购买意向产生影响。然而，研究结果仍未得出结论。在本研究中，我们将自我概念和群体相似性视为在线评论评级影响消费者购买意向的关键因素。我们进一步研究了消费者的自我建构在影响消费者对在线评论的归属感和诊断性方面所起的作用。为验证假设，我们对通过亚马逊机械土耳其（MTurk）收集的 276 名受试者进行了 2（在线评论评分）×2（群体相似性）×2（自我建构）方差分析，并使用对比分析和 PROCESS 宏模型 12 进行了交互效应分析和调节中介分析。我们的研究结果表明，具有相互依存自我结构的消费者在购买意向方面对评论评分和群体相似性都很敏感。当群体相似度和在线评论评分都很高时，他们会表现出积极的购买意向。然而，当群体相似度较低时，他们的购买意向不受评论评级的影响。相反，无论群体相似度如何，当在线评论评分较高时，具有独立自我概念的消费者会表现出更积极的购买意向。此外，我们的研究还强调了感知诊断性和归属感在网络评论评分、群体相似性、自我建构和购买意向之间的中介作用。研究结果表明，感知诊断性和归属感具有明显的间接效应，这意味着在线评论评分对购买意向的影响是由这两个变量中介的。我们的研究成果提供了有关在线评论的理论和实践意义，并为在线消费者行为领域的未来研究提出了新的途径。
{"title":"The Impact of Online Reviews on Consumers’ Purchase Intentions: Examining the Social Influence of Online Reviews, Group Similarity, and Self-Construal","authors":"Yunjeong Ahn, Jieun Lee","doi":"10.3390/jtaer19020055","DOIUrl":"https://doi.org/10.3390/jtaer19020055","url":null,"abstract":"Consumers often rely on evaluations such as online reviews shared by other consumers when making purchasing decisions. Online reviews have emerged as a crucial marketing tool that offers a distinct advantage over traditional methods by fostering trust among consumers. Previous studies have identified group similarity between consumers and reviewers as a key variable with a potential impact on consumer responses and purchase intention. However, the results remain inconclusive. In this study, we identify self-construal and group similarity as key factors in the influence of online review ratings on consumers’ purchase intentions. We further investigate the role of consumers’ self-construal in shaping consumers’ perceptions of online reviews in terms of belongingness and diagnosticity. To test the hypothesis, we conducted a 2 (online review rating) × 2 (group similarity) × 2 (self-construal) ANOVA on 276 subjects collected through Amazon Mechanical Turk (MTurk), and contrast analysis and PROCESS macro model 12 were used for the interaction effect analysis and moderated mediation analysis. Our findings reveal that consumers with an interdependent self-construal are sensitive to both review ratings and group similarity with regards to their purchase intentions. They demonstrate a positive purchase intention when both group similarity and online review ratings are high. However, their purchase intention is not influenced by review ratings when group similarity is low. Conversely, consumers with an independent self-construal exhibit a more positive purchase intention when the online review rating is high, irrespective of group similarity. Additionally, our study highlights the mediating roles of perceived diagnosticity and belongingness in the relationship between online review ratings, group similarity, self-construal, and purchase intentions. Results show significant indirect effects for perceived diagnosticity and belongingness, meaning that the impact of online review ratings on purchase intention is mediated by these two variables. The outcomes of our research offer theoretical and practical implications concerning online reviews and suggest new avenues for future research in the area of online consumer behavior.","PeriodicalId":46198,"journal":{"name":"Journal of Theoretical and Applied Electronic Commerce Research","volume":"37 1","pages":""},"PeriodicalIF":5.6,"publicationDate":"2024-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140932052","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：