Dongsong Zhang

Instructional video in e-learning: Assessing the impact of interactive video on learning effectiveness

Interactive video in an e-learning system allows proactive and random access to video content. Our empirical study examined the influence of interactive video on learning outcome and learner satisfaction in e-learning environments. Four different settings were studied: three were e-learning environments--with interactive video, with non-interactive video, and without video. The fourth was the traditional classroom environment. Results of the experiment showed that the value of video for learning effectiveness was contingent upon the provision of interactivity. Students in the e-learning environment that provided interactive video achieved significantly better learning performance and a higher level of learner satisfaction than those in other settings. However, students who used the e-learning environment that provided non-interactive video did not improve either. The findings suggest that it may be important to integrate interactive instructional video into e-learning systems.

The Impact of Individualism-Collectivism, Social Presence, and Group Diversity on Group Decision Making Under Majority Influence

Majority influence is the attempt by a majority of group members to impose their common position on group dissenters during group decision making. Because of globalization, the use of cross-cultural teams in group tasks is becoming increasingly common. The objective of this study was to investigate how national culture, social presence, and group diversity may affect majority influence in a group decision-making context. A total of 183 groups participated in a large-scale empirical experiment at multiple sites. The results show that the national culture of group minorities has a significant impact on majority influence and that the use of computer-mediated communication can reduce majority influence. The findings have both theoretical and practical implications for improving the outcome and the effectiveness of group decision making in cross-cultural environments.

EXPRS: An extended pagerank method for product feature extraction from online consumer reviews

Abstract Online consumer product reviews are a main source for consumers to obtain product information and reduce product uncertainty before making a purchase decision. However, the great volume of product reviews makes it tedious and ineffective for consumers to peruse individual reviews one by one and search for comments on specific product features of their interest. This study proposes a novel method called EXPRS that integrates an extended PageRank algorithm, synonym expansion, and implicit feature inference to extract product features automatically. The empirical evaluation using consumer reviews on three different products shows that EXPRS is more effective than two baseline methods.

An Ontology-Supported Misinformation Model: Toward a Digital Misinformation Library

The importance of research on misinformation has received wide recognition. Two major challenges faced by this research community are the lack of theoretical models and the scarcity of misinformation in support of such research. This paper aims to address the aforementioned challenges by conceptualizing misinformation and enabling the interoperability of misinformation. In particular, a representation and a model of misinformation are proposed through surveying, synthesizing, and explicating existing work in the field. Moreover, ontology is used to represent the proposed model. The ontology-supported misinformation model can not only guide future misinformation research but also lay the foundation for building a digital misinformation library by advancing our knowledge on misinformation and by improving its sharing, management, and reuse. In addition, we present a formal methodology for managing misinformation in a digital library, and suggest future research directions related to the misinformation model.

A heuristic approach to establishing punctuation convention in instant messaging

Instant Messaging (IM) features informal writing styles such as the omission of punctuation. Punctuation plays an important role in representing prosody and facilitating syntactic processing during communication. The discrepancy between the recognized importance and actual inadequate usage of punctuation in IM calls for establishing punctuation convention for more effective online communication. The research uniquely reported here addressed two research questions. The first was whether punctuation had an impact on the effectiveness of IM. The results of an empirical study showed that the majority of surveyed participants perceived punctuation to be somewhat important. This led to the investigation of the second research question: how to restore omitted punctuation in instant messaging to help develop punctuation convention effectively? We designed and implemented a technical solution for recovering punctuation based on heuristics rules and an evaluation of this approach showed satisfactory performance. A detailed analysis of punctuation in archived instant messages revealed several patterns of omitted punctuation. The findings of this research not only advance our understanding of the stylistic convention, but also provide positive evidence for establishing punctuation convention in IM. As IM continues to pervade daily communication, punctuation convention in IM deserves closer attention.

Discourse cues to deception in the case of multiple receivers

Behavioral cues to deception are instrumental in detecting deception. As one of the primary sources of deception behavior, text has been analyzed at the level of sub-sentence or message but not the discourse of interaction. Additionally, empirical studies on cues to deception in the case of multiple receivers remain nonexistent. To fill these voids, we propose a discourse framework and six hypotheses about deception behaviors in a multi-receiver environment. The deception behaviors are operationalized by discourse features based on an analysis of real-world data. The results of statistical analysis validate the efficacy of discourse features in discriminating deceivers from truth-tellers.