Yung-Ming Li

Increasing trust in mobile commerce through design aesthetics

The growth of mobile commerce (m-commerce) has motivated a better understanding of how trust can be built on a mobile device. Researchers have previously examined design aesthetics (or visual aesthetics) of mobile website and incorporated a hedonic component of enjoyment in m-commerce domain, but the relationship between design aesthetics of mobile website design and customer trust in m-commerce has been rarely investigated. In this study, design aesthetics was enhanced to include a website characteristics component as important to trust development on the mobile Internet. This model was examined through an empirical study involving 200 subjects using structural equation modeling techniques. Our research found that design aesthetics did significantly impact website characteristics component, especially customization, perceived usefulness and ease of use, all of which were ultimately shown to have significant explanatory power in affecting customer trust.

A diffusion mechanism for social advertising over microblogs

Social media have increasingly become popular platforms for information dissemination. Recently, companies have attempted to take advantage of social advertising to deliver their advertisements to appropriate customers. The success of message propagation in social media depends greatly on the content relevance and the closeness of social relationships. In this paper, considering the factors of user preference, network influence, and propagation capability, we propose a diffusion mechanism to deliver advertising information over microblogging media. Our experimental results show that the proposed model could provide advertisers with suitable targets for diffusing advertisements continuously and thus efficiently enhance advertising effectiveness.

A social recommender mechanism for e-commerce: Combining similarity, trust, and relationship

Abstract Online business transactions and the success of e-commerce depend greatly on the effective design of a product recommender mechanism. This study proposes a social recommender system that can generate personalized product recommendations based on preference similarity, recommendation trust, and social relations. Compared with traditional collaborative filtering approaches, the advantage of the proposed mechanism is its comprehensive consideration of recommendation sources. Accordingly, our experimental results show that the proposed model outperforms other benchmark methodologies in terms of recommendation accuracy. The proposed framework can also be effectively applied to e-commerce retailers to promote their products and services.

Identifying influential reviewers for word-of-mouth marketing

The key to word-of-mouth marketing is to discover the potential influential nodes for efficiently spreading product impressions. In this paper, a framework combined with mining techniques, a modified PMI measure, and an adaptive RFM model is proposed to evaluate the influential power of online reviewers. An artificial neural network is adopted to identify the target reviewers and a well-developed trust mechanism is utilized for effectiveness evaluation. This proposed framework is verified by the data collected from Epinions.com, one of the most popular online product review websites. The experimental results show that the proposed model could accurately identify which reviewers to select to become the influential nodes. This proposed approach can be exploited in effectively carrying out online word-of-mouth marketing, which can save a lot of resources in finding customers.

Deriving market intelligence from microblogs

Given their rapidly growing popularity, microblogs have become great sources of consumer opinions. However, in the face of unique properties and the massive volume of posts on microblogs, this paper proposes a framework that provides a compact numeric summarization of opinions on such platforms. The proposed framework is designed to cope with the following tasks: trendy topics detection, opinion classification, credibility assessment, and numeric summarization. An experiment is carried out on Twitter, the largest microblog website, to prove the effectiveness of the proposed framework. We find that the consideration of user credibility and opinion subjectivity is essential for aggregating microblog opinions. The proposed mechanism can effectively discover market intelligence (MI) for supporting decision-makers.

Discovering influencers for marketing in the blogosphere

Discovering influential bloggers will not only allow us to understand better the social activities taking place in the blogosphere, but will also provide unique opportunities for sales and advertising. In this paper, we develop an MIV (marketing influential value) model to evaluate the influential strength and identify the influential bloggers in the blogosphere. We analyze three dimensions of blog characteristics (network-based, content-based, and activeness-based factors) and utilize an artificial neural network (ANN) to discover potential bloggers. Based on peer and official evaluations, the experimental results show that the proposed framework outperforms two social-network-based methods (out-degree and betweenness centrality algorithms) and two content-based mechanisms (review rating and popular author approaches). The proposed framework can be effectively applied to support marketers or advertisers in promoting their products or services.

A synthetical approach for blog recommendation: Combining trust, social relation, and semantic analysis

Weblog is a good paradigm of online social network which constitutes web-based regularly updated journals with reverse chronological sequences of dated entries, usually with blogrolls on the sidebars, allowing bloggers link to favorite site which they are frequently visited. In this study we propose a blog recommendation mechanism that combines trust model, social relation and semantic analysis and illustrates how it can be applied to a prestigious online blogging system - wretch in Taiwan. By the results of experimental study, we found a number of implications from the Weblog network and several important theories in domain of social networking were empirically justified. The experimental evaluation reveals that the proposed recommendation mechanism is quite feasible and promising.

A social recommender mechanism for location-based group commerce

With the rapid growth of social media platforms, numerous group commerce websites, which exploit both the advantages of price discounts and experience value, have emerged. Moreover, the popularity of sophisticated mobile devices brings great commercial opportunities for local store to gain publicity. In this research, considering user preference, geographic convenience, and friends’ influence, a group-coupon recommender system is proposed for promoting location-sensitive products. The results of experiments conducted on Facebook indicate that the proposed mechanism could accurately recommend products and satisfactorily provide a companion list of to customers, significantly increasing willingness to purchase by taking advantage of the power of social influence.

Knowledge sharing in communities of practice: A game theoretic analysis

This research applies game theory to analyze the incentives of knowledge-sharing activities in various types of communities of practice (COPs), characterized by individual profiles and decision structures. Indeed, individual decision making results in the under-provision of knowledge; however, the benefit of knowledge sharing may be raised by IT investment and suitable incentive mechanisms we study here. In general conditions, improving communication and collaboration technologies should be prior to developing data mining technologies. However, when the number of community members is sufficiently small and the heterogeneity of the expected value of knowledge among community members is sufficiently large, developing data mining technologies should be considered more important than the other if most community members are low-type ones. On the other hand, based on a screening technique, we find that the benefit of knowledge sharing in the incomplete information setting can be the same as that in the complete information setting if the cost of more efficient community member is smaller than that of less efficient one.

A social recommender mechanism for improving knowledge sharing in online forums

Nowadays, online forums have become a useful tool for knowledge management in Web-based technology. This study proposes a social recommender system which generates discussion thread and expert recommendations based on semantic similarity, profession and reliability, social intimacy and popularity, and social network-based Markov Chain (SNMC) models for knowledge sharing in online forum communities. The advantage of the proposed mechanism is its relatively comprehensive consideration of the aspects of knowledge sharing. Accordingly, results of our experiments show that with the support of the proposed recommendation mechanism, requesters in forums can easily find similar discussion threads to avoid spamming the same discussion. In addition, if the requesters cannot find qualified discussion threads, this mechanism provides a relatively efficient and active way to find the appropriate experts.