Effect of writing style on social support in online health communities: A theoretical linguistic analysis framework

In online health communities (OHCs), patients can exchange social support through text-based communication. However, research on how various linguistic characteristics of patients' communication in these communities affect their social support outcomes remains limited. This study performs linguistic profiling on OHC participants based on a large dataset and empirically evaluates how lexical, syntactic, semantic, and pragmatic features affect users' communication and social support outcomes. The results show that lexical richness in health-related vocabulary negatively correlates with receiving informational support. The readability and brevity of written texts have positive relationships with incoming social support. Writing longer sentences positively correlates with receiving informational support but negatively correlates with receiving emotional support. Expressing negative sentiment leads to higher chances of receiving both types of social support. The use of terms related to perception and body parts increases the chances of receiving emotional support. The use of terms related to perception words additionally correlates to higher chances of receiving informational support. To receive social supports, being logical in expressions is also critical. Furthermore, the relationships between shared health language and social support are determined by the word category and social support type.     

StackExchange问答社区知识传播

StackExchange是目前最流行的问答社区集结地之一.本文利用StackExchange中具有美国地理信息的用户构建StackExchange问答社区在美国境内的知识传播图谱,对传播网络的统计特征进行了分析,提取出问答社区类网站的传播模式,获取得到网络用户的知识分享方式.我们发现StackExchange中的问答社区在分享知识过程中,传播源往往不止一个.同时,我们为问答社区构建了知识传播图谱,发现这些传播图谱具有相似的统计特征,这意味着不同的问答社区可能具有类似的知识传播模式.     

The structure and dynamics of knowledge network in domain-specific Q&A sites: a case study of stack overflow

Programming-specific Q&A sites (e.g., Stack Overflow) are being used extensively by software developers for knowledge sharing and acquisition. Due to the cross-reference of questions and answers (note that users also reference URLs external to the Q&A site. In this paper, URL sharing refers to internal URLs within the Q&A site, unless otherwise stated), knowledge is diffused in the Q&A site, forming a large knowledge network. In Stack Overflow, why do developers share URLs? How is the community feedback to the knowledge being shared? What are the unique topological and semantic properties of the resulting knowledge network in Stack Overflow? Has this knowledge network become stable? If so, how does it reach to stability? Answering these questions can help the software engineering community better understand the knowledge diffusion process in programming-specific Q&A sites like Stack Overflow, thereby enabling more effective knowledge sharing, knowledge use, and knowledge representation and search in the community. Previous work has focused on analyzing user activities in Q&A sites or mining the textual content of these sites. In this article, we present a methodology to analyze URL sharing activities in Stack Overflow. We use open coding method to analyze why users share URLs in Stack Overflow, and develop a set of quantitative analysis methods to study the structural and dynamic properties of the emergent knowledge network in Stack Overflow. We also identify system designs, community norms, and social behavior theories that help explain our empirical findings. Through this study, we obtain an in-depth understanding of the knowledge diffusion process in Stack Overflow and expose the implications of URL sharing behavior for Q&A site design, developers who use crowdsourced knowledge in Stack Overflow, and future research on knowledge representation and search.     

What are mobile developers asking about? A large scale study using stack overflow

The popularity of mobile devices has been steadily growing in recent years. These devices heavily depend on software from the underlying operating systems to the applications they run. Prior research showed that mobile software is different than traditional, large software systems. However, to date most of our research has been conducted on traditional software systems. Very little work has focused on the issues that mobile developers face. Therefore, in this paper, we use data from the popular online Q&A site, Stack Overflow, and analyze 13,232,821 posts to examine what mobile developers ask about. We employ Latent Dirichlet allocation-based topic models to help us summarize the mobile-related questions. Our findings show that developers are asking about app distribution, mobile APIs, data management, sensors and context, mobile tools, and user interface development. We also determine what popular mobile-related issues are the most difficult, explore platform specific issues, and investigate the types (e.g., what, how, or why) of questions mobile developers ask. Our findings help highlight the challenges facing mobile developers that require more attention from the software engineering research and development communities in the future and establish a novel approach for analyzing questions asked on Q&A forums.     

A longitudinal study of leader influence in sustaining an online community

Previous research suggests that online leaders play an important role in sustaining community activities. Although the research has contributed to our understanding of how leaders develop effective ways to operate a community, most only provide a snapshot view of online leadership, thus paying little attention to changes in leaders in a communal context. In this study, we adopt the theory of networked influence to investigate the dynamics of online leadership using a longitudinal analysis. Data were collected from an online community in operation for 10 years. By conducting social network analysis using qualitative methods, we identified several types of emerging and coexisting online leadership, i.e., responsive expert leader, multiboard connectors, and social bond leader. The community’s sustainability did not rely on the same leaders throughout its temporal development but rather a “relay event” involving passing on the baton among different leaders with their specific leadership styles, which had a significant positive impact on the sustainability of user participation.     

How students emerge as learning leaders in small group online discussions

In this study, we examined the role of leadership styles and multi-dimensional learner engagement in how students emerge as learning leaders in asynchronous online discussions. Grounded in the conceptual framework of two dominant leadership styles of transformational and transactional leadership, this study applies the two leadership styles—transformational leadership and transactional leadership—to the Leader Identification Method (LIM) which defines three types of leader roles (i.e., full, transactional and attractive facilitator) in online learning. We collected data from 20 students enrolled in a graduate-level online course that required participation in 12-week discussion activities. Results of the longitudinal data analyses show that person-focused, transformational leadership and active participation in online discussions were significant factors that enabled students to emerge as learning leaders. Students are more likely to become leaders by exhibiting transformational leadership behaviour and productively interacting with one another in an online discussion community.     

Understanding knowledge contributors’ satisfaction in transactional virtual communities: A cost–benefit trade-off perspective

This study investigates knowledge contributors’ satisfaction with a distinct type of virtual communities (i.e., transactional virtual communities, TVCs), where knowledge sharing is guided mainly under the principle of economic exchange, and cost–benefit tradeoff is the primary motive for knowledge sharing. Drawing upon the goal attainment theory, we examine the effects of two types of benefits (i.e., extrinsic and intrinsic) and two types of costs (i.e., actual and opportunity) on knowledge contributors’ satisfaction, and highlight the mediating role of perceived net goal attainment. A field survey with 205 subjects in a TVC in China is conducted to test the research model.     

What makes the difference? An empirical comparison of fusion strategies for multimodal language analysis

Multimodal video sentiment analysis is a rapidly growing area. It combines verbal (i.e., linguistic) and non-verbal modalities (i.e., visual, acoustic) to predict the sentiment of utterances. A recent trend has been geared towards different modality fusion models utilizing various attention, memory and recurrent components. However, there lacks a systematic investigation on how these different components contribute to solving the problem as well as their limitations. This paper aims to fill the gap, marking the following key innovations. We present the first large-scale and comprehensive empirical comparison of eleven state-of-the-art (SOTA) modality fusion approaches in two video sentiment analysis tasks, with three SOTA benchmark corpora. An in-depth analysis of the results shows that the attention mechanisms are the most effective for modelling crossmodal interactions, yet they are computationally expensive. Second, additional levels of crossmodal interaction decrease performance. Third, positive sentiment utterances are the most challenging cases for all approaches. Finally, integrating context and utilizing the linguistic modality as a pivot for non-verbal modalities improve performance. We expect that the findings would provide helpful insights and guidance to the development of more effective modality fusion models.     

<Emphasis Type="Bold">Impact of object manipulation,customization and social loafing on competencies management in 3D Virtual Worlds</Emphasis>

3D Virtual Worlds (VW) are rich and promising collaboration tools limitedly introduced to support competence management, yet, extensively used to enhance knowledge sharing (KS) and support knowledge application (KA). Nevertheless, KS and KA represent a challenging medium to leverage individual as well as organization’s competencies. Characterized by a realistic visual dimension in representing work environment and a growing capacity of simulation, 3D platforms facilitate and value competence formation. Present study analyzes role of 3D VW technology unique characteristics (i.e. object manipulation and avatar and 3D environment customization) and specific personal character social loafing, on competencies acquisition. Individual performance and organizational performance were measured to assess individual and organizational competences. Answers from 144 users of 3D VWs were analyzed. Results show that social loafing has significant negative effect on knowledge sharing. Customization and object manipulation have significant, yet small moderating effect on 3D VW technology use and knowledge sharing. KS subsequent effect on KA, individual and organizational competencies are significant. Limitations and new research directions are presented.     

How Does Sentiment Content of Product Reviews Make Diffusion Different?

ABSTRACT

The current study is focusing on diffusion and adoption of new digital artifacts. The goal is to explore the social role of user-generated content (UGC) during the diffusion process of digital products in the context of online social networks. Data collection is conducted on 154 new digital products during a two-year timeframe. Results of the study provide a deeper insight into the influence of sentiment content on new product diffusion and how such a web system (i.e., online social networks) can help to enable a process of value co-creation. The overall finding shows that sentiment content has a positive, but dynamic relationship with diffusion of digital products.

The study sheds light on the crowding power and the long-tail effect in online social networks. Findings also offer valuable implications for organizations to set up their strategic vision in terms of information dissemination, digital marketing, and customer relationship management.     

Effects of information technologies,department characteristics and individual roles on improving knowledge sharing visibility: a qualitative case study

Knowledge sharing visibility (KSV) is a critical environmental factor which can reduce social loafing in knowledge sharing (KS). This is especially true in ICT-based KS in learning organisations. As such, it is imperative that we better understand how to design technology enabled knowledge management systems (KMS) to support high KSV. This article examines the impact of knowledge management technology functions (e.g. tracking, knowledge storing) on KSV through qualitative analysis of 16 semi-structured interviews with participants in a Chinese company. Impact and implications of use for their existing KMS are examined. This article also examined the effects of department characteristics (i.e. group size and task characteristics) and individual roles (i.e. employee positions) on the IT–KSV relationship. Results encourage applied statistical, tracking, knowledge distribution and knowledge storing functions for monitoring explicit KS, and suggest integration of visualised knowledge maps with communication tools (e.g. Instant Messenger (IM)) to support visibility for implicit KS. Findings also suggest that KM technologies are more salient on improving KSV in large department with routine tasks, and that low-level employees may have more positive attitude on accepting communication tools on sharing knowledge. Extension to use of Web 2.0 technologies (e.g. weblogs) in KMS is also explored.     

Effect of linguistic disfluency on consumer satisfaction: Evidence from an online knowledge payment platform

The popularity of online knowledge payment platforms enables online users to disseminate paid knowledge via voice communication. However, such communication provided by users with little professional teaching skills commonly tends to contain linguistic disfluency, which is a potential determinant of consumer satisfaction of paid knowledge products. This study examines how linguistic disfluency inherent in paid knowledge products impacts consumer satisfaction and the moderating effects of two consumer knowledge aspects, namely expertise and familiarity. Based on processing fluency theory, we build a theoretical model to illuminate relationships between consumer satisfaction, linguistic disfluency, and consumer knowledge. Leveraging data from Zhihu Live, a leading online knowledge payment platform, we find that linguistic disfluency is negatively associated with consumer satisfaction; nevertheless, this negative association disappears or turns into a positive effect for consumers with high expertise and low familiarity. Our study offers implications for platforms to accomplish high consumer satisfaction and further improve user retention and revenue.     

Towards identifying unresolved discussions in student online forums

Online discussion is a popular form of web-based computer-mediated communication and is a dominant medium for cyber communities in areas of information sharing, customer support and distributed education. Automatic tools for analyzing online discussions are highly desirable for better information management and assistance. For example, a summary of student Q&A discussions or unresolved questions can help the instructor assess student dialogue efficiently, which can lead to better instructor guidance for student learning by discussion. This paper presents an approach for classifying student discussions according to a set of discourse structures, and identifying discussions with confusion or unanswered questions. Inspired by the existing spoken dialogue analysis approaches, we first define a set of forum “speech acts” (F-SAs) that represent roles that individual messages play in threaded Q&A discussions, such as questions, raising issues, and answers. We then model discourse structures in discussion threads using the F-SAs, such as whether a question was replied to with an answer. Finally, we use such discourse structures in classifying and identifying discussions with unanswered questions or unresolved issues. We performed an analysis of the discussion thread classifiers and the system showed accuracies from 0.79 to 0.87 on several discussion classification problems. This analysis of human conversation via online discussions provides a basis for development of future information extraction and intelligent assistance techniques for online discussions.     

How the R community creates and curates knowledge: an extended study of stack overflow and mailing lists

One of the effects of social media’s prevalence in software development is the many flourishing communities of practice where users share a common interest. These large communities use many different communication channels, but little is known about how they create, share, and curate knowledge using such channels. In this paper, we report a mixed methods study of how one community of practice, the R software development community, creates and curates knowledge associated with questions and answers (Q&A) in two of its main communication channels: the R tag in Stack Overflow and the R-Help mailing list. The results reveal that knowledge is created and curated in two main forms: participatory, where multiple users explicitly collaborate to build knowledge, and crowdsourced, where individuals primarily work independently of each other. Moreover, we take a unique approach at slicing the data based on question score and participation activities over time. Our study reveals participation patterns, showing the existence of prolific contributors: users who are active across both channels and are responsible for a large proportion of the answers, serving as a bridge of knowledge. The key contributions of this paper are: a characterization of knowledge artifacts that are exchanged by this community of practice; the reasons why users choose one channel over the other; and insights on the community participation patterns, which indicate an evolution of the community and a shift from knowledge creation to knowledge curation.     

The effects of social media based brand communities on brand community markers,value creation practices,brand trust and brand loyalty

Social media based brand communities are communities initiated on the platform of social media. In this article, we explore whether brand communities based on social media (a special type of online brand communities) have positive effects on the main community elements and value creation practices in the communities as well as on brand trust and brand loyalty. A survey based empirical study with 441 respondents was conducted. The results of structural equation modeling show that brand communities established on social media have positive effects on community markers (i.e., shared consciousness, shared rituals and traditions, and obligations to society), which have positive effects on value creation practices (i.e., social networking, community engagement, impressions management, and brand use). Such communities could enhance brand loyalty through brand use and impression management practices. We show that brand trust has a full mediating role in converting value creation practices into brand loyalty. Implications for practice and future research opportunities are discussed.     

Topic extraction from extremely short texts with variational manifold regularization

Machine Learning - With the emerging of massive short texts, e.g., social media posts and question titles from Q&amp;A systems, discovering valuable information from them is increasingly...     

The influence of dispositions and Internet motivation on online communication satisfaction and relationship closeness

Guided by the Uses and Gratifications (U&G) perspective, this study examined the influence of unwillingness to communicate, loneliness, Internet-use motives, and Internet (CMC) use and interaction (amount and types of use and self-disclosure) in online communication satisfaction and online relationship closeness. There were 261 participants in this study. Overall, participants who perceived their face-to-face communication to be rewarding, used CMC for self-fulfillment, and disclosed their personal feelings to others tended to feel close to their online partners. Moreover, those who used the Internet for purposes of self-fulfillment and affection and intended to disclose their feelings to others felt satisfied with their online communication. The associations among the constructs extend our knowledge of the U&G theoretical model, how and why people communicate interpersonally in CMC settings, and the influence of individual differences on CMC for relational communication.     

SENTIMENT ASSESSMENT OF TEXT BY ANALYZING LINGUISTIC FEATURES AND CONTEXTUAL VALENCE ASSIGNMENT

Text is not only an important medium to describe facts and events, but also to effectively communicate information about the writer's positive or negative sentiment underlying an opinion, or to express an affective or emotional state, such as happiness, fearfulness, surpriseness, and so on. We consider sentiment assessment and emotion sensing from text as two different problems, whereby sentiment assessment is the task that we want to solve first. Thus, this article presents an approach to sentiment assessment, i.e., the recognition of negative or positive valence of a sentence. For the purpose of sentiment recognition from text, we perform semantic dependency analysis on the semantic verb frames of each sentence, and then apply a set of rules to each dependency relation to calculate the contextual valence of the whole sentence. By employing a domain-independent, rule-based approach our system is able to automatically identify sentence-level sentiment. A linguistic tool called “SenseNet” has been developed to recognize sentiments in text, and to visualize the detected sentiments. We conducted several experiments with a variety of datasets containing data from different domains. The obtained results indicate significant performance gains over existing state-of-the-art approaches.     

An Ironic Fist in a Velvet Glove: Creative Mis-Representation in the Construction of Ironic Similes

Irony is an effective but challenging mode of communication that allows a speaker to express viewpoints rich in sentiment with concision, sharpness and humour. Creative irony is especially common in online documents that express subjective and deeply-felt opinions, and thus represents a significant obstacle to the accurate analysis of sentiment in web texts. In this paper we look at one commonly used framing device for linguistic irony—the simile—to show how even the most creative uses of irony are often marked in ways that make them computationally feasible to detect. We conduct a very large corpus analysis of web-harvested similes to identify the most interesting characteristics of ironic comparisons, and provide an empirical evaluation of a new algorithm for separating ironic from non-ironic similes.