Pub Date : 2020-02-15DOI: 10.1080/10919392.2020.1718056
Yen-Hsien Lee, Chih-Ping Wei, P. H. Hu, T. Cheng, Ci-Wei Lan
ABSTRACT Content-based recommendation techniques usually require a large number of training examples for model construction, which however may not always be available in many real-world scenarios. To address the training data availability constraint common to the content-based approach, we develop a collaborative expansion-based approach to expand the size of training examples, which could lead to improved content-based recommendations. We use a book rating data set collected from Amazon to evaluate our proposed method and compare its performance against those of two salient benchmark techniques. The results show that our method outperforms the benchmark techniques consistently and significantly. Our method expands the size of training examples for a focal customer by leveraging the available preferences of his or her referent group, and thereby better supports personalized recommendations than existing techniques that solely follow content-based or collaborative filtering, without incurring costs to identify, collect, and analyze additional information. This study reveals the value and feasibility of collaborative expansion as a viable means to increase training size for the focal customer and thus address the training data availability constraint that seriously hinders the performance of content-based recommender systems.
{"title":"Small Clues Tell: a Collaborative Expansion Approach for Effective Content-Based Recommendations","authors":"Yen-Hsien Lee, Chih-Ping Wei, P. H. Hu, T. Cheng, Ci-Wei Lan","doi":"10.1080/10919392.2020.1718056","DOIUrl":"https://doi.org/10.1080/10919392.2020.1718056","url":null,"abstract":"ABSTRACT Content-based recommendation techniques usually require a large number of training examples for model construction, which however may not always be available in many real-world scenarios. To address the training data availability constraint common to the content-based approach, we develop a collaborative expansion-based approach to expand the size of training examples, which could lead to improved content-based recommendations. We use a book rating data set collected from Amazon to evaluate our proposed method and compare its performance against those of two salient benchmark techniques. The results show that our method outperforms the benchmark techniques consistently and significantly. Our method expands the size of training examples for a focal customer by leveraging the available preferences of his or her referent group, and thereby better supports personalized recommendations than existing techniques that solely follow content-based or collaborative filtering, without incurring costs to identify, collect, and analyze additional information. This study reveals the value and feasibility of collaborative expansion as a viable means to increase training size for the focal customer and thus address the training data availability constraint that seriously hinders the performance of content-based recommender systems.","PeriodicalId":54777,"journal":{"name":"Journal of Organizational Computing and Electronic Commerce","volume":"30 1","pages":"111 - 128"},"PeriodicalIF":2.9,"publicationDate":"2020-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/10919392.2020.1718056","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47393511","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-02-13DOI: 10.1080/10919392.2020.1724765
J. Estêvão, M. J. Carneiro, L. Teixeira
ABSTRACT The fast development in information and communication technologies transformed the tourism sector, raising relevant questions regarding the role of destination management organizations (DMOs) and the most appropriate way to implement and manage online platforms adopted by these organizations – destination management systems (DMSs). Nevertheless, the research concerning DMSs' adoption and management is scarce, mostly conceptual and highly fragmented, usually corresponding to theoretical discussions on a small set of adoption or management issues or to analysis of very specific examples of DMSs. This paper aims to overcome gaps in previous literature by deeply analyzing relevant factors for the adoption and management of this kind of systems. In-depth interviews were conducted with relevant organizations in DMS development and several American and European DMOs. The content analysis of the discourses resulted in a framework encompassing an adoption and management model – including reasons and challenges regarding DMSs’ adoption, management models, benefits resulting from DMS adoption – as well as current challenges and future perspectives for DMSs. The findings provide relevant theoretical and practical contributions. Theoretically, the paper highlights some discrepancies between the literature and the present study regarding the concept of DMSs, as well as reasons and challenges associated with their adoption and management. The need to rethink the role and management of these systems is also remarked. From a practical perspective, the framework proposed can be used by DMOs and other stakeholders engaged in the management of tourism destinations, in order to ensure the successful implementation and management of DMSs.
{"title":"Destination management systems’ adoption and management model: proposal of a framework","authors":"J. Estêvão, M. J. Carneiro, L. Teixeira","doi":"10.1080/10919392.2020.1724765","DOIUrl":"https://doi.org/10.1080/10919392.2020.1724765","url":null,"abstract":"ABSTRACT The fast development in information and communication technologies transformed the tourism sector, raising relevant questions regarding the role of destination management organizations (DMOs) and the most appropriate way to implement and manage online platforms adopted by these organizations – destination management systems (DMSs). Nevertheless, the research concerning DMSs' adoption and management is scarce, mostly conceptual and highly fragmented, usually corresponding to theoretical discussions on a small set of adoption or management issues or to analysis of very specific examples of DMSs. This paper aims to overcome gaps in previous literature by deeply analyzing relevant factors for the adoption and management of this kind of systems. In-depth interviews were conducted with relevant organizations in DMS development and several American and European DMOs. The content analysis of the discourses resulted in a framework encompassing an adoption and management model – including reasons and challenges regarding DMSs’ adoption, management models, benefits resulting from DMS adoption – as well as current challenges and future perspectives for DMSs. The findings provide relevant theoretical and practical contributions. Theoretically, the paper highlights some discrepancies between the literature and the present study regarding the concept of DMSs, as well as reasons and challenges associated with their adoption and management. The need to rethink the role and management of these systems is also remarked. From a practical perspective, the framework proposed can be used by DMOs and other stakeholders engaged in the management of tourism destinations, in order to ensure the successful implementation and management of DMSs.","PeriodicalId":54777,"journal":{"name":"Journal of Organizational Computing and Electronic Commerce","volume":"30 1","pages":"110 - 89"},"PeriodicalIF":2.9,"publicationDate":"2020-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/10919392.2020.1724765","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43871123","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-02-12DOI: 10.1080/10919392.2020.1718457
Yuangying Liang, Terence T. Ow, Xiaolei Wang
ABSTRACT Online community managers are seeking effective ways to encourage users to exhibit prosocial behaviors that help sustain the growth and effectiveness of online communities. One tactic is to set up small groups to build relationships and facilitate communications. In addition to social norms formed and shared among all community users, individuals are also subjected to potential influence from peers with whom they directly communicated within the group. This study integrated social exchange theory with group influence theory to investigate how the influences of reputation and reciprocity on users’ contributions were modified under two categories of group influences, i.e., informational and normative influence. Based on a longitudinal observation of over 3,000 members from 72 subgroups in an online community, we developed a cross-level moderation model to enrich our understanding of users’ contribution behavior with the influence of group performances. This study provides guidelines for online community administrators to create and foster effective communities for knowledge contribution and exchange.
{"title":"How do group performances affect users’ contributions in online communities? A cross-level moderation model","authors":"Yuangying Liang, Terence T. Ow, Xiaolei Wang","doi":"10.1080/10919392.2020.1718457","DOIUrl":"https://doi.org/10.1080/10919392.2020.1718457","url":null,"abstract":"ABSTRACT Online community managers are seeking effective ways to encourage users to exhibit prosocial behaviors that help sustain the growth and effectiveness of online communities. One tactic is to set up small groups to build relationships and facilitate communications. In addition to social norms formed and shared among all community users, individuals are also subjected to potential influence from peers with whom they directly communicated within the group. This study integrated social exchange theory with group influence theory to investigate how the influences of reputation and reciprocity on users’ contributions were modified under two categories of group influences, i.e., informational and normative influence. Based on a longitudinal observation of over 3,000 members from 72 subgroups in an online community, we developed a cross-level moderation model to enrich our understanding of users’ contribution behavior with the influence of group performances. This study provides guidelines for online community administrators to create and foster effective communities for knowledge contribution and exchange.","PeriodicalId":54777,"journal":{"name":"Journal of Organizational Computing and Electronic Commerce","volume":"30 1","pages":"129 - 149"},"PeriodicalIF":2.9,"publicationDate":"2020-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/10919392.2020.1718457","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42926511","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-01-02DOI: 10.1080/10919392.2020.1713698
F. Martínez-López, Yangchun Li, Changyuan Feng, Irene Esteban-Millat
ABSTRACT Buy buttons are a call-to-action feature directing viewers to a follow-up purchase page, which allows users to make direct and actual purchases through social platforms. This paper examines two different direct purchase behaviors (general purchase behavior and impulse purchase behavior) through a social platform with buy buttons, and, for the purposes of study, proposes a model based on the standard learning hierarchy sequence for users’ perceived ease of purchase from a social platform, their attitude toward shopping on it, and, finally, their general and impulse purchase responses toward a seller’s item through the platform. Our study used the Chinese survey platform, Wjx.cn, to recruit participants, who were users of the Chinese social platform, WeChat. The model was then tested by structural equation modeling with both an estimation sample and a validation sample. The result showed that ease of purchase positively affects attitude toward using the social platform for shopping, which in turn positively influences two purchase intentions. General purchase intention also positively affects impulse purchase intention. These findings can also offer useful and valuable implications for social platforms wanting to monetize via buy buttons and sellers wanting to use buy buttons to increase direct purchases via social platforms.
{"title":"Purchasing through Social Platforms with Buy Buttons: A Basic Hierarchical Sequence","authors":"F. Martínez-López, Yangchun Li, Changyuan Feng, Irene Esteban-Millat","doi":"10.1080/10919392.2020.1713698","DOIUrl":"https://doi.org/10.1080/10919392.2020.1713698","url":null,"abstract":"ABSTRACT Buy buttons are a call-to-action feature directing viewers to a follow-up purchase page, which allows users to make direct and actual purchases through social platforms. This paper examines two different direct purchase behaviors (general purchase behavior and impulse purchase behavior) through a social platform with buy buttons, and, for the purposes of study, proposes a model based on the standard learning hierarchy sequence for users’ perceived ease of purchase from a social platform, their attitude toward shopping on it, and, finally, their general and impulse purchase responses toward a seller’s item through the platform. Our study used the Chinese survey platform, Wjx.cn, to recruit participants, who were users of the Chinese social platform, WeChat. The model was then tested by structural equation modeling with both an estimation sample and a validation sample. The result showed that ease of purchase positively affects attitude toward using the social platform for shopping, which in turn positively influences two purchase intentions. General purchase intention also positively affects impulse purchase intention. These findings can also offer useful and valuable implications for social platforms wanting to monetize via buy buttons and sellers wanting to use buy buttons to increase direct purchases via social platforms.","PeriodicalId":54777,"journal":{"name":"Journal of Organizational Computing and Electronic Commerce","volume":"30 1","pages":"67 - 87"},"PeriodicalIF":2.9,"publicationDate":"2020-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/10919392.2020.1713698","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45257146","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-01-02DOI: 10.1080/10919392.2019.1671739
G. Vlahakis, Evangelia Kopanaki, Dimitris Apostolou
ABSTRACT To procure products and materials in the context of modern, convoluted supply chains, companies need to consider a variety of available options regarding trading partners, products, materials and services, as well as deal with changing circumstances. Therefore, they seek for solutions that enable them to increase their efficiency, improve the effectiveness of collaboration with trading partners, deal with unexpected events and make proactive decisions. To address these issues, this paper focuses on the purchasing process and proposes an approach that enhances decision making, leading to proactive actions/recommendations to ensure cost-effectiveness. It supports selection of partners, monitors events pertaining to the purchasing process and enables proactive cost processing for potential supplier/shipper reconsideration, order cancellation or continuation. To enable proactive cost handling, we adopt and use the framework ‘detect – forecast – decide – act’. To support forecast and represent the causal relationship between events and supply chain actors, we use a Bayes Network. Finally, to verify the effectiveness of our proposed model, we develop a system and test it experimentally, through numerical simulation. Our results show that our proactive decision making method can lead to improved order efficiency, agility and cost management.
{"title":"Proactive decision making in supply chain procurement","authors":"G. Vlahakis, Evangelia Kopanaki, Dimitris Apostolou","doi":"10.1080/10919392.2019.1671739","DOIUrl":"https://doi.org/10.1080/10919392.2019.1671739","url":null,"abstract":"ABSTRACT To procure products and materials in the context of modern, convoluted supply chains, companies need to consider a variety of available options regarding trading partners, products, materials and services, as well as deal with changing circumstances. Therefore, they seek for solutions that enable them to increase their efficiency, improve the effectiveness of collaboration with trading partners, deal with unexpected events and make proactive decisions. To address these issues, this paper focuses on the purchasing process and proposes an approach that enhances decision making, leading to proactive actions/recommendations to ensure cost-effectiveness. It supports selection of partners, monitors events pertaining to the purchasing process and enables proactive cost processing for potential supplier/shipper reconsideration, order cancellation or continuation. To enable proactive cost handling, we adopt and use the framework ‘detect – forecast – decide – act’. To support forecast and represent the causal relationship between events and supply chain actors, we use a Bayes Network. Finally, to verify the effectiveness of our proposed model, we develop a system and test it experimentally, through numerical simulation. Our results show that our proactive decision making method can lead to improved order efficiency, agility and cost management.","PeriodicalId":54777,"journal":{"name":"Journal of Organizational Computing and Electronic Commerce","volume":"30 1","pages":"28 - 50"},"PeriodicalIF":2.9,"publicationDate":"2020-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/10919392.2019.1671739","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49233446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-01-02DOI: 10.1080/10919392.2020.1736833
Dave Chatterjee
Dear Prospective Authors: I am delighted to inform you that this game-changing publishing initiative for bringing the best actionable insights on cybersecurity is entering its third year. The revie...
{"title":"Bringing the Best Actionable Insights on Cybersecurity: A Call for Papers","authors":"Dave Chatterjee","doi":"10.1080/10919392.2020.1736833","DOIUrl":"https://doi.org/10.1080/10919392.2020.1736833","url":null,"abstract":"Dear Prospective Authors: I am delighted to inform you that this game-changing publishing initiative for bringing the best actionable insights on cybersecurity is entering its third year. The revie...","PeriodicalId":54777,"journal":{"name":"Journal of Organizational Computing and Electronic Commerce","volume":"30 1","pages":"I - III"},"PeriodicalIF":2.9,"publicationDate":"2020-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/10919392.2020.1736833","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49013937","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-01-02DOI: 10.1080/10919392.2020.1755790
D. O’Leary
ABSTRACT This paper examines some of the issues for research needs from information systems and information technology researchers, elicited as part of the COVID-19 pandemic. We investigate a number of issues, including facilitating work while social distancing, contactless commerce, person recognition, when wearing masks or in other crisis situations, COVID-19 apps and their impact on issues such as privacy, crowdsourcing, donating data, tracking cases, etc. We also investigate the notion of people that have had COVID-19 and thus may not be vulnerable to the disease, versus, those that are still vulnerable to the disease. In addition, we examine several supply chain issues, such as changing patterns of supply and demand, fragile supply chains and autonomic supply chains. Further, we investigate a number of emerging issues and the roles of data, big data, and analytics in the area of changing and evolving work and their impact on organizations and electronic commerce. Finally, we conclude with a consideration of the merging of life and work and the issue of work–life balance.
{"title":"Evolving Information Systems and Technology Research Issues for COVID-19 and Other Pandemics","authors":"D. O’Leary","doi":"10.1080/10919392.2020.1755790","DOIUrl":"https://doi.org/10.1080/10919392.2020.1755790","url":null,"abstract":"ABSTRACT This paper examines some of the issues for research needs from information systems and information technology researchers, elicited as part of the COVID-19 pandemic. We investigate a number of issues, including facilitating work while social distancing, contactless commerce, person recognition, when wearing masks or in other crisis situations, COVID-19 apps and their impact on issues such as privacy, crowdsourcing, donating data, tracking cases, etc. We also investigate the notion of people that have had COVID-19 and thus may not be vulnerable to the disease, versus, those that are still vulnerable to the disease. In addition, we examine several supply chain issues, such as changing patterns of supply and demand, fragile supply chains and autonomic supply chains. Further, we investigate a number of emerging issues and the roles of data, big data, and analytics in the area of changing and evolving work and their impact on organizations and electronic commerce. Finally, we conclude with a consideration of the merging of life and work and the issue of work–life balance.","PeriodicalId":54777,"journal":{"name":"Journal of Organizational Computing and Electronic Commerce","volume":"30 1","pages":"1 - 8"},"PeriodicalIF":2.9,"publicationDate":"2020-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/10919392.2020.1755790","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44189548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-01-02DOI: 10.1080/10919392.2020.1713686
X. Fang, T. Rajkumar, Mark P. Sena, C. Holsapple
ABSTRACT Relying on participants with full time work experience, this study investigates if the national culture of an individual, and the culture dimensions of uncertainty avoidance, in-group collectivism and power distance affect first impression bias reduction within a personnel decision context. This study also examines whether online video is superior to online text in reducing first impression bias in a hiring decision. We find that none of the above culture dimensions nor the type of medium used significantly affect first impression bias. However, we do find that national culture, operationalized as a dummy variable, reduces first impression bias to a significant degree.
{"title":"National culture, online medium type, and first impression bias","authors":"X. Fang, T. Rajkumar, Mark P. Sena, C. Holsapple","doi":"10.1080/10919392.2020.1713686","DOIUrl":"https://doi.org/10.1080/10919392.2020.1713686","url":null,"abstract":"ABSTRACT Relying on participants with full time work experience, this study investigates if the national culture of an individual, and the culture dimensions of uncertainty avoidance, in-group collectivism and power distance affect first impression bias reduction within a personnel decision context. This study also examines whether online video is superior to online text in reducing first impression bias in a hiring decision. We find that none of the above culture dimensions nor the type of medium used significantly affect first impression bias. However, we do find that national culture, operationalized as a dummy variable, reduces first impression bias to a significant degree.","PeriodicalId":54777,"journal":{"name":"Journal of Organizational Computing and Electronic Commerce","volume":"30 1","pages":"51 - 66"},"PeriodicalIF":2.9,"publicationDate":"2020-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/10919392.2020.1713686","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48930012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-02DOI: 10.1080/10919392.2019.1671738
Brian I. Spaid, Bonnie S. O’Neill, Terence T. Ow
ABSTRACT The ubiquitous nature of mobile internet devices (i.e., smartphones and tablet computers) has led to an increase of their use within the retail environment as a shopping assistive technology. Consumers use them for a variety of shopping-related tasks, the most significant of which is researching product information. The use of these devices has clearly impacted how consumers shop, but what is not clear is how these devices affect shopper satisfaction, trust in the retailer and subsequent shopper intentions. The purpose of this paper is to better understand these relationships and extend existing research on the use of mobile internet devices in the retail industry. Several hypotheses are offered, and survey data from a nationwide random sample of consumers tested the hypotheses using structural equation modeling. Results indicate that shoppers’ satisfaction and trust in an online information source creates a spill-over effect on satisfaction and trust toward the retailer. Additionally, retailer repatronage intentions increase as a result of this spill-over effect. Contributions to emerging mobile marketing literature and theory, managerial implications, and future research recommendations are discussed.
{"title":"The upside of showrooming: How online information creates positive spill-over for the brick-and-mortar retailer","authors":"Brian I. Spaid, Bonnie S. O’Neill, Terence T. Ow","doi":"10.1080/10919392.2019.1671738","DOIUrl":"https://doi.org/10.1080/10919392.2019.1671738","url":null,"abstract":"ABSTRACT The ubiquitous nature of mobile internet devices (i.e., smartphones and tablet computers) has led to an increase of their use within the retail environment as a shopping assistive technology. Consumers use them for a variety of shopping-related tasks, the most significant of which is researching product information. The use of these devices has clearly impacted how consumers shop, but what is not clear is how these devices affect shopper satisfaction, trust in the retailer and subsequent shopper intentions. The purpose of this paper is to better understand these relationships and extend existing research on the use of mobile internet devices in the retail industry. Several hypotheses are offered, and survey data from a nationwide random sample of consumers tested the hypotheses using structural equation modeling. Results indicate that shoppers’ satisfaction and trust in an online information source creates a spill-over effect on satisfaction and trust toward the retailer. Additionally, retailer repatronage intentions increase as a result of this spill-over effect. Contributions to emerging mobile marketing literature and theory, managerial implications, and future research recommendations are discussed.","PeriodicalId":54777,"journal":{"name":"Journal of Organizational Computing and Electronic Commerce","volume":"29 1","pages":"294 - 315"},"PeriodicalIF":2.9,"publicationDate":"2019-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/10919392.2019.1671738","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41584179","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-08-29DOI: 10.1080/10919392.2019.1654350
Abdessamad Benlahbib, E. Nfaoui
ABSTRACT Amazon, eBay, IMDb as well as several websites provide a convenient platform where users share their opinions on any entities without hindrance. Though those opinions are too many to be examined one by one, this is why a general reputation value will help people make a decision toward a target entity (purchase, download, rent …). This fact makes reputation generation task very challenging because an inaccurate reputation system will directly damage the credibility and popularity of the target entity. This paper aims to improve a recent work that handles the task of generating reputation based on fuzing and mining opinions expressed in natural languages and user feedback ratings. Therefore, we have proposed a hybrid approach that, (i) separates reviews into positive and negative based on their sentiment polarity by applying the two classifiers Naïve Bayes and Linear Support Vector Machine (LSVM), (ii) groups positive and negative reviews into principal opinion sets based on their semantic relations, (iii) calculates a custom reputation value separately for positive and negative groups by considering some statistics of principal opinion sets and finally (iv) computes the final reputation value using Weighted Arithmetic Mean. Experimental results show a significant improvement with respect to recent work.
{"title":"A hybrid approach for generating reputation based on opinions fusion and sentiment analysis","authors":"Abdessamad Benlahbib, E. Nfaoui","doi":"10.1080/10919392.2019.1654350","DOIUrl":"https://doi.org/10.1080/10919392.2019.1654350","url":null,"abstract":"ABSTRACT Amazon, eBay, IMDb as well as several websites provide a convenient platform where users share their opinions on any entities without hindrance. Though those opinions are too many to be examined one by one, this is why a general reputation value will help people make a decision toward a target entity (purchase, download, rent …). This fact makes reputation generation task very challenging because an inaccurate reputation system will directly damage the credibility and popularity of the target entity. This paper aims to improve a recent work that handles the task of generating reputation based on fuzing and mining opinions expressed in natural languages and user feedback ratings. Therefore, we have proposed a hybrid approach that, (i) separates reviews into positive and negative based on their sentiment polarity by applying the two classifiers Naïve Bayes and Linear Support Vector Machine (LSVM), (ii) groups positive and negative reviews into principal opinion sets based on their semantic relations, (iii) calculates a custom reputation value separately for positive and negative groups by considering some statistics of principal opinion sets and finally (iv) computes the final reputation value using Weighted Arithmetic Mean. Experimental results show a significant improvement with respect to recent work.","PeriodicalId":54777,"journal":{"name":"Journal of Organizational Computing and Electronic Commerce","volume":"30 1","pages":"27 - 9"},"PeriodicalIF":2.9,"publicationDate":"2019-08-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1080/10919392.2019.1654350","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41994162","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"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：