Social Shopping: The Good, the Bad, and the Ugly

Permanent URI for this collection


Recent Submissions

Now showing 1 - 4 of 4
  • Item
    Understanding User Participation and Interaction in Online Shopping Communities from the Social and Relational Perspectives
    ( 2020-01-07) Xu, Yu ; Lee, Michael
    The combination of online shopping and social media has contributed to the increase of social shopping activities. Technological advancements allow people with similar interests and experience to share, comment, and discuss about shopping from anywhere and at any time, leading to the emergence of online shopping communities (OSCs). This study reports on lab experiments and focus groups with 24 participants who actively engage in OSCs. We identify how informational support and social support affect user participation and relationships, the impact of social structure on interpersonal relationship formation between community members, and the development of desire to be socially connected with others through real-time conversations. Based on the findings, we discuss a series of design recommendations to facilitate users' emotional exchange and contribution behavior in OSCs, such as enhanced conversational interaction, and collaborative mini-tasks in a social shopping context.
  • Item
    Double Deep Features for Apparel Recommendation System
    ( 2020-01-07) Lu, Yichi ; Duan, Yufeng ; Saga, Ryosuke
    This study describes a recommendation system embedded in the double features extracted by convolutional neural networks (CNNs). Several probabilistic models, such as probabilistic matrix factorization (PMF)-based approaches, have been utilized for recommendation systems based on a CNN model. Each recommendation algorithm utilizes a single CNN model to extract precise features about documents and pictures, and the systems with CNN have contributed in improving the performance in rating prediction. Meanwhile, the systems for some items should consider at least two precise features simultaneously, and the extension to embed multiple CNN models is necessary. However, methods that integrate multiple CNN-based features into existing recommendation systems, such as PMF, are not available. Thus, this study proposes a novel probabilistic model that integrates double CNNs into PMF. For apparel goods, two trained CNNs from document and image shape features are combined, and the latent variables of users and items are optimized based on the vectorized features of CNNs and rating. Extensive experiments demonstrate that our model outperforms other recommendation models.
  • Item
    How Does the Power of Crowdvoting Affect Purchase Decisions? Effects of Majority and Minority Influence in Online Rating Systems
    ( 2020-01-07) Chen, Chi-Wen
    Online rating systems gather review scores on products from different customers’, creating collective opinions and accumulating the power formed by the crowdvoting. Such the power of the crowdvoting generates two influences: majority and minority influences. Both of which may form a signal that guides or misleads product/service evaluation and in turn purchase decision. This study draws from signaling theory to examine the effects of (1) majority, (2) minority influence and (3) number of reviewers on online shoppers’ perceived product quality and perceived social risk and how they further influence purchase intention. We conducted a scenario-based experiment to test the research model and employed a 2x2x2 full factorial design. A total of 371 undergraduates had participated. The results of this study suggest that majority influence increases perceived product quality and decreases perceived social risk, influencing shoppers’ purchase decision. Implications for theory, practice, and future research directions are discussed.
  • Item
    Introduction to the Minitrack on Social Shopping: The Good, the Bad, and the Ugly
    ( 2020-01-07) Sadovykh, Valeria ; Peko, Gabrielle ; Sundaram, David