TOWARD COLLECTIVE INTELLIGENCE OF ONLINE COMMUNITIES:A PRIMITIVE CONCEPTUAL MODEL

Inspired by the ideas of Swarm Intelligence and the ＂global brain＂, a concept of ＂community intelligence＂ is suggested in the present paper, reflecting that some ＂intelligent＂ features may emerge in a Web-mediated online community from interactions and knowledge-transmissions between the community members. This possible research field of community intelligence is then examined under the backgrounds of ＂community＂ and ＂intelligence＂ researches. Furthermore, a conceptual model of community intelligence is developed from two views. From the structural view, the community intelligent system is modeled as a knowledge supernetwork that is comprised of triple interwoven networks of the media network, the human network, and the knowledge network. Furthermore, based on a dyad of knowledge in two forms of ＂knowing＂ and ＂knoware＂, the dynamic view describes the basic mechanics of the formation and evolution of ＂community intelligence＂. A few relevant research issues are shortly discussed on the basis of the proposed conceptual model.

A comparative analysis of major Chinese and English online question-answering communities

This paper compares 12 representative Chinese and English online questionanswering communities(Q&A communities) based on their basic functions, interactive modes, and customized services. An empirical experiment from a comparative perspective was also conducted on them by using 12 questions representing for four types of questions,which are assigned evenly to three different subject fields so as to examine the task performance of these 12 selected online Q&A communities. Our goal was to evaluate those online Q&A communities in terms of their quality and efficiency for answering questions posed to them. It was hoped that our empirical research would yield greater understanding and insights to the working intricacy of these online Q&A communities and hence their possible further improvement.

Topic Sentiment Analysis in Online Learning Community from College Students

Purpose:Opinion mining and sentiment analysis in Online Learning Community can truly reflect the students’learning situation,which provides the necessary theoretical basis for following revision of teaching plans.To improve the accuracy of topic-sentiment analysis,a novel model for topic sentiment analysis is proposed that outperforms other state-of-art models.Methodology/approach:We aim at highlighting the identification and visualization of topic sentiment based on learning topic mining and sentiment clustering at various granularitylevels.The proposed method comprised data preprocessing,topic detection,sentiment analysis,and visualization.Findings:The proposed model can effectively perceive students’sentiment tendencies on different topics,which provides powerful practical reference for improving the quality of information services in teaching practice.Research limitations:The model obtains the topic-terminology hybrid matrix and the document-topic hybrid matrix by selecting the real user’s comment information on the basis of LDA topic detection approach,without considering the intensity of students’sentiments and their evolutionary trends.Practical implications:The implication and association rules to visualize the negative sentiment in comments or reviews enable teachers and administrators to access a certain plaint,which can be utilized as a reference for enhancing the accuracy of learning content recommendation,and evaluating the quality of their services.Originality/value:The topic-sentiment analysis model can clarify the hierarchical dependencies between different topics,which lay the foundation for improving the accuracy of teaching content recommendation and optimizing the knowledge coherence of related courses.

Evaluating Group Formation in Virtual Communities

In this paper, we are interested in answering the following research question: "Is it possible to form effective groups in virtual communities by exploiting trust information without significant overhead, similarly to real user communities?"In order to answer this question, instead of adopting the largely used approach of exploiting the opinions provided by all the users of the community(called global reputation), we propose to use a particular form of reputation, called local reputation. We also propose an algorithm for group formation able to implement the proposed procedure to form effective groups in virtual communities. Another interesting question is how to measure the effectiveness of groups in virtual communities. To this aim we introduce the index in a measure of the effectiveness of the group formation. We tested our algorithm by realizing some experimental trials on real data from the real world EPINIONS and CIAO communities, showing the significant advantages of our procedure w.r.t. another prominent approach based on traditional global reputation.

Web Based Supportive Intervention for Families Living with Schizophrenia—An Open Trial

Background: Web based modalities should be explored to support families living with mental illness. A web based tool including a psychoeducative module, a diary and a password protected forum was developed aimed at relatives’ of a person with schizophrenia to alleviate daily life. Aim: The aim of the present study was to explore participants’ use of the web based tool with focus on the forum and its potential health and psychosocial benefits. Methods: Nineteen persons participated in this explorative open trial. The forum posts were analyzed using content analysis. Self-rating instruments assessing caregiver burden, stigma and the tool’s usability were analyzed with descriptive statistics. Results: The qualitative analysis resulted in four main categories and subcategories describing relatives’ situation and interaction in the forum: Caring for a Person with Schizophrenia, Crisis and Care, Secrecy vs Openness, and Interaction and Social Support. Experiences of caregiver burden, but also fulfillment with caregiving tasks were reported. Concealing or hiding the family’s mental illness was common, but also the ability to use inner strength to cope with stigma and discrimination. The mean usability score was 59 (70 = good). Conclusion: Web based support can help address some of the families’ needs of support, although it encompasses certain limitations. Patient rights and the availability of resources, especially in cases of emergency, need to be made easily visible and accessible to alleviate families’ burden.

How Social Network Position Relates to Knowledge Building in Online Learning Communities?

Social Network Analysis,Statistical Analysis,Content Analysis and other research methods were used to research online learning communities at Capital Normal University,Beijing.Analysis of the two online courses resulted in the following conclusions:(1)Social networks of the two online courses form typical core-periphery structures;(2)Social networks of the two online courses contain“structural holes,”where some actors position themselves to become potential opinion-leaders within their social networks;(3)Actors,variously positioned within a core-periphery structure,show quite significant differences in terms of knowledge building;(4)Taking“structural holes”into account,there exist considerable differences in knowledge building between opinion-leaders and non opinion-leaders;(5)Actors in the“core”and“structural hole”positions have very different characteristics in terms of knowledge building.These actors in particular play important roles in online learning communities,impacting on the level of the constructed knowledge.

Identification of ChatGPT answers and physician answers in the online medical community

ChatGPT changes the way of knowledge production and information space structure of human society.In the healthcare industry,ChatGPT's powerful question-and-answer capability will drive its application in automated question answering in online healthcare communities.However,because ChatGPT answers are limited by factors such as the quality of data sets,their authority and accuracy cannot be guaranteed,and they are prone to misdiagnosis and damage to life and health.Therefore,the identification of ChatGPT answers in online medical communities with physician answers is crucial.In this paper,we collected medical question-answering data generated by the Haodafu platform and ChatGPT,respectively,constructed feature vectors from semantic features,syntactic features,and the fusion of both,and combined different feature vectors with XGBoost models to construct BERT-XGBoost,POS-XGBoost and Merge-XGBoost models for identifying ChatGPT answers and physician answers in online medical communities.The three models achieved accuracy rates of 0.960,0.968,and 0.986,respectively.The difference in performance between the three models reflects the degrees of variation in different features of ChatGPT answers versus physician answers.The results indicate that the differences between ChatGPT and physicians in syntactic features,i.e.,linguistic expression habits,are greater than their differences in semantic features,i.e.,specific content suggestions.

Online Healthcare Community Interaction Dynamics

With the increasing dilemma of the rapid global demand for healthcare services(often in the presence of limited resources),how to creatively allocate and use healthcare resources across a widespread population has become a salient issue.Online healthcare communities(OHCs)are regarded as a potential ICT-based partial solution.In contrast to traditional healthcare,online doctor-patient interaction is unlimited in terms of time and space limitations while an OHC is exposed to the whole community.These characteristics are key to achieving synergistic doctor-patient interaction and community development in the longer term.In order to explore the nature of doctor-patient interaction dynamics in an OHC,we systematically investigate doctor-patient interaction dynamics from the dual perspectives of doctor and patient.Our doctor-patient interaction dual-cycle model has been built based on six doctor-patient interaction processes(i.e.,searching,choosing,knowledge sharing,providing,receiving and balancing).According to our dual-cycle model,four key managerial issues in OHC(information asymmetry,incentive mechanisms,service delivery processes and interaction mechanisms)have been identified as examples.Discussion and directions for future research,with challenges as well as opportunities,have been elaborated.A broad view with fruitful research potential is ensured and new theories and methods ultimately provide implications for effectively and efficiently allocating scarce healthcare resources to a broader population.

Improving Friend Recommendation for Online Learning with Fine-Grained Evolving Interest

Friend recommendation plays a key role in promoting user experience in online social networks(OSNs).However,existing studies usually neglect users’fine-grained interest as well as the evolving feature of interest,which may cause unsuitable recommendation.In particular,some OSNs,such as the online learning community,even have little work on friend recommendation.To this end,we strive to improve friend recommendation with fine-grained evolving interest in this paper.We take the online learning community as an application scenario,which is a special type of OSNs for people to learn courses online.Learning partners can help improve learners’learning effect and improve the attractiveness of platforms.We propose a learning partner recommendation framework based on the evolution of fine-grained learning interest(LPRF-E for short).We extract a sequence of learning interest tags that changes over time.Then,we explore the time feature to predict evolving learning interest.Next,we recommend learning partners by fine-grained interest similarity.We also refine the learning partner recommendation framework with users’social influence(denoted as LPRF-F for differentiation).Extensive experiments on two real datasets crawled from Chinese University MOOC and Douban Book validate that the proposed LPRF-E and LPRF-F models achieve a high accuracy(i.e.,approximate 50%improvements on the precision and the recall)and can recommend learning partners with high quality(e.g.,more experienced and helpful).

Negative Sentiment Shift on a Chinese Movie-Rating Website

Shifting to negativity is more and more prevalent in online communities and may play a key role in group polarization.While current research indicates a close relationship between group polarization and negative sentiment,they often link negative sentiment shifts with echo chambers and misinformation within echo chambers.In this work,we explore the sentiment drift using over 4 million comments from a Chinese online movie-rating community that is less affected by misinformation than other mainstream online communities and has no echo chamber structures.We measure the sentiment shift of the community and users of different engagement levels.Our analysis reveals that while the community does not show a tendency toward negativity,users of higher engagement levels are generally more negative,considering factors like the different movies they consume.The results indicate a fitting-in process,suggesting the possible mechanism of group identity on sentiment shift on social media platforms.These findings also provide guidance on web design to tackle the negativity issue and expand sentiment shift analysis to non-English contexts.