Introduction to the special section on learning and security for multi-agent systems

This special section features six articles that provide an overview of the emerging research topics at the intersection learning, security, and multi-agent systems. Recent years have witnessed a surge in the number of works at their intersections, and they have appeared in system and control communities as well as many other communities in artificial intelligence, cyber–physical systems, and economics. The articles in this special section give accessible and comprehensive tutorials and surveys for a broad systems and control audience, covering topics including adversarial machine learning, multi-agent reinforcement learning, cyber resilience, resilient control systems, and game design. It is hopeful that this special section will spawn future interest and cross-disciplinary collaborations in this emerging transdisciplinary research area.     

Uncovering research trends and topics of communities in machine learning

This paper aims to uncover the research topics in machine learning research communities in a scientific collaboration network (SCN) to enhance the characteristic of systems such as retrieval or recommendation in intelligence-based systems. The existing research mainly focuses on the community evolution and measurement of typical features of the network. It is however unexplored how to identify the research interest of the communities along with authors in each community. A dataset is prepared consisting of 21,906 scientific articles from six top journals in the field of machine learning published from 1988 to 2017. An integrated approach combining the author-topic (AT) model with communities using through the directed affiliations (CoDA) method is explored to identify the research interest of the communities in a scientific collaboration network. The top rank communities are identified using the crank network community prioritization method. Finally, the similarity and dissimilarity of research interest in communities across decades are uncovered using the cosine similarity. The experimental results demonstrate the effectiveness and efficacy of the proposed technique. This study may be helpful for upcoming researchers to explore the research trends and topics in machine learning research communities.

     

Optimum design of electronic communities as economic entities

Electronic communities can be designed to organize consumers, to pool their purchasing power, and to guide their purchasing decisions. Such commercial electronic communities have the potential to facilitate the creation of novel marketplaces, and even radically change the buyer-seller interaction, as physical communities did throughout the history. Commercial electronic communities are groups of consumers that participate in the marketplace as a single unit. In addition to bargaining power gained from such bundling, such communities can expand markets by reducing market uncertainty, and they have the potential to drastically reduce consumers’ transaction costs, by facilitating group transactions and bulk purchasing. Communities are characterized by their size, their pricing strategy, and their membership characteristics. Analytical models and numeric analysis is utilized to compute the optimum size of a community for given market characteristics. Two major community pricing strategies are analyzed to improve the community design, and the conditions are derived where one dominates the other. Finally, market segmentation techniques are introduced to control the membership characteristics of the community to further improve the design. Levent V. Orman is a professor of Information Systems at Cornell University, Graduate School of Management. He received a Ph.D. degree from Northwestern University. He has taught courses and written articles on electronic commerce, database management, decision support systems, and expert systems. His recent articles appeared in Journal of Information Technology and Management, Journal of MIS, Acta Informatica, and IEEE Transactions on Knowledge and Data Engineering. He is the associate editor of the Journal of Database Management, and serves on the editorial board of the Journal of Information Technology and Management.     

The new neighbourhood in the internet era: network communities serving local communities

The past two decades have witnessed many attempts to transform online communities in new neighbourhoods of the Internet era. In particular, one of the most interesting applications of Internet Technologies in this field have been ‘network communities’, that differ from online communities because they refer to a specific territory and, for this reason, serve as a social catalyst for the corresponding territorial community. Network communities, as virtual neighbourhoods, have the purpose of allowing a better understanding of physical ones, contributing to the creation and the proliferation of services most suited to the needs of residents. For this reason, municipalities and local governments should consider the opportunity to exploit network communities as useful tools for local community management. Following this lead, this article analyses a real case study and highlights the existence of a positive correlation between a constructive utilisation of a network community by its members, their sense of community and the degree of their involvement in local problems.     

Guest Editors' Introduction: Internet Access to Scientific Data

The experimental and experiential nature of many sciences requires that researchers capture huge volumes of data for which they propose theories to explain or model the data. Simulations, queries, and data mining can generate very large derived data sets. The Internet and associated technologies (such as the Web and the Grid) have become the de facto medium for sharing raw data, analyzed information, and derived knowledge for many technical and scientific communities. Considerable research and commercial activity has focused on this area, but many unresolved issues remain. The articles in this theme section illustrate some of the work that is currently being done to help address some key challenges.     

Speech emotion recognition research: an analysis of research focus

This article analyses research in speech emotion recognition (“SER”) from 2006 to 2017 in order to identify the current focus of research, and areas in which research is lacking. The objective is to examine what is being done in this field of research. Searching on selected keywords, we extracted and analysed 260 articles from well-known online databases. The analysis indicates that SER research is an active field of research, dozens of articles being published each year in journals and conference proceedings. The majority of articles concentrate on three critical aspects of SER, namely (1) databases, (2) suitable speech features, and (3) classification techniques to maximize the recognition accuracy of SER systems. Having carried out association analysis of the critical aspects and how they influence the performance of the SER system in term of recognition accuracy, we found that certain combination of databases, speech features and classifiers influence the recognition accuracy of the SER system. We have also suggested aspects of SER that could be taken into consideration in future works based on our review.     

Mobile communities: How viable are their business models? An exemplary investigation of the leisure industry

Communities (especially Virtual Communities) of Interest have been the focus of substantial discussion in academic literature. This paper addresses Communities of Interest within the leisure industry and discusses possible business models for the parties operating the platform. The described community platform is an innovative value added service concept for a mobile coordination support for individuals—A Mobile Community Support System. In this paper we extend the discussion about mobile communities to hybrid communities. The communities are hybrid in two ways: they use two different access channels, the Web and mobile devices, and they are built on real-world leisure communities that constitute themselves in the form of buddy lists in the virtual world of an ICT supported platform. We briefly depict the state of the art of IT in the leisure industry and describe the empirical aspects of the project objectives of the MCOR (Mobile Community Online Reservation) system. We conclude with some final remarks about design considerations and a blueprint for future research. Felix Hampe holds a chair for Corporate Communication Systems and is Director of the Institute for IS Research at the Faculty of Informatics of the University of Koblenz-Landau in Germany. He studied at the Free University of Berlin and worked later for the University of Bielefeld and the Philipps-University of Marburg prior to his appointment to Koblenz. In 2004/2005, he spent one year as a visiting professor at the University of South Australia, School of Computer and Information Systems. Beside his research interest in application aspects of communication systems, Professor Hampe started very early research in the area of mobile applications and especially mobile commerce. He was cofounder and board member of the Mobile Application Research Center (MARC), a German network for joint research on mobile business. Professor Hampe authored several international conference articles in the area and served for many international conferences.     

基于群体行为的社交媒体中水军分析

社交媒体是当下非常热门的一种互联网应用。在发生公共事件时,许多当事人雇佣公关公司在社交媒体上发布虚假信息来影响舆情。这部分为公关公司所服务的社交媒体账号称为水军。水军在当下的中国社交媒体中有泛滥的趋势。基于水军的群体行为分析社交媒体中的水军集团。定义了情感社会网络和情感社会网络中的团的概念;设计了一个分析框架,包括提出了情感社会网络中发现社区,以及从社区中发现对立的派别（称为团）的算法。从微博的评论数据构建情感社会网络,并发现情感社会网络中的团,可以识别水军,而且可以考察社交媒体中的水军集团的特性。采用人工标注的数据集进行了实验。     

Locating and parsing bibliographic references in HTML medical articles

The set of references that typically appear toward the end of journal articles is sometimes, though not always, a field in bibliographic (citation) databases. But even if references do not constitute such a field, they can be useful as a preprocessing step in the automated extraction of other bibliographic data from articles, as well as in computer-assisted indexing of articles. Automation in data extraction and indexing to minimize human labor is key to the affordable creation and maintenance of large bibliographic databases. Extracting the components of references, such as author names, article title, journal name, publication date and other entities, is therefore a valuable and sometimes necessary task. This paper describes a two-step process using statistical machine learning algorithms, to first locate the references in HTML medical articles and then to parse them. Reference locating identifies the reference section in an article and then decomposes it into individual references. We formulate this step as a two-class classification problem based on text and geometric features. An evaluation conducted on 500 articles drawn from 100 medical journals achieves near-perfect precision and recall rates for locating references. Reference parsing identifies the components of each reference. For this second step, we implement and compare two algorithms. One relies on sequence statistics and trains a Conditional Random Field. The other focuses on local feature statistics and trains a Support Vector Machine to classify each individual word, followed by a search algorithm that systematically corrects low confidence labels if the label sequence violates a set of predefined rules. The overall performance of these two reference-parsing algorithms is about the same: above 99% accuracy at the word level, and over 97% accuracy at the chunk level.     

Acceptance of Health-Related ICT among Elderly People Living in the Community: A Systematic Review of Qualitative Evidence

There are a growing number of seniors and a growing need for health-related ICT (Information and Communication Technology) solutions to allow seniors to live independently in their own homes and communities. We need to have a better understanding of how and why seniors use or do not use health-related ICT in such settings so we can improve our solutions. In order to synthesize existing knowledge, we did a systematic literature review using Scopus and PubMed. We searched for both review articles and primary qualitative studies. Eleven review articles and 31 primary research articles were included in the study. We structured our findings using the UTAUT2 acceptance model developed by Venkatesh et al. Our findings show that seniors want health-related ICT that gives them independence, safety, and security, allows them to socialize and manage their own health, and helps them in their daily activities. They need to easily get help if they have problems using services, get tailored training, and get help during use. Lack of privacy and safety and stigma are some of the reported barriers. Health-related ICT at home is different than both consumer and institutional ICT. We need more research in order to develop a specialized and operationalized acceptance model for health-related ICT use among seniors. Our mapping to UTAUT2 is a step in this direction and suggests a possible specialization of this model.     

Community building and knowledge sharing by individuals with disabilities using social media

The use of social media to share information, enhance learning, and connect with an online community has grown rapidly over the past 10 years. As social media becomes a more common tool in both formal and informal education, it is imperative to understand how it is used by individuals with disabilities. Through a systematic study of the literature, 215 articles on social media used by individuals with disabilities were selected and 29 selected for in-depth thematic analysis. Six major themes were identified: community, cyberbullying, self-esteem, self-determination, access to technology, and accessibility. To confirm these six categories, we expanded our search, yielding an additional 30 articles, for a total 59 articles reviewed in-depth. Interactions between individuals with disabilities within online communities often had the goal of acquiring knowledge or learning new information. A communities of practice theoretical framework is used to discuss interactions among the elements of social media design, learning, and the building of community by individuals with disabilities.     

A Storm you Really Need to Weather

Packet Storm (www.packetstorm.securify.com) is a security site with an interesting mission statement: “To ensure that Packet Storm is a security resource that provides the mechanism for both the underground and the corporate communities to converge and direct their efforts towards sharing security information.” Describing themselves as the largest and most up-to-date security database in the world, about half their content is submitted from interested parties. Accepting the fact that information must be shared in order to crack the myriad of security threats, Packet Storm follows a strict policy of full-disclosure, publishing all pertinent information that they receive on security-related materials. In fact, they openly invite all of us to submit relevant information or well-written articles for inclusion in their archives and new files section.     

The nature of virtual communities

The impressive development of electronic communication techniques has given rise to virtual communities. The nature of these computer-mediated communities has been the subject of much recent debate. Are they ordinary social groups in electronic form, or are they fundamentally different from traditional communities? Understanding virtual communities seems a prerequisite for the design of better communication systems. To clarify this debate, we will resort to the classical sociological distinction between small traditional communities (based on personal relations) and modern social groups (bound by looser, more impersonal links). We will argue that the discussion about virtual communities is often vitiated by a simplistic assimilation to traditional communities, whereas they may be in fact quite different and much more impersonal. Virtual communities are often bound by reference to common objects or goals, and not by personal relations. In this respect, virtual communities are just another example of a long-term evolution of modern society toward more abstract social relationships.     

Who will lead and who will follow: Identifikation einflussreicher Nutzer in Online Social Networks

Along with the explosive growth of the phenomenon Online Social Networks (OSN), identifying influential users in OSN has received a great deal of attention in recent years. However, the development of practical approaches for identifying them is still in its infancy. By means of a structured literature review, the authors analyze and synthesize the publications particularly from two perspectives. From a research perspective, they find that existing approaches mostly build on users’ connectivity and activity but hardly consider further characteristics of influential users. Moreover, they outline two major research streams. It becomes apparent that most marketing-oriented articles draw on real-world data of OSN, while more technology-oriented papers rather have a theoretical approach and mostly evaluate their artifacts by means of formal proofs. The authors find that a stronger collaboration between the scientific Business and Information Systems Engineering (BISE) and Marketing communities could be mutually beneficial. With respect to a practitioner’s perspective, they compile advice on the practical application of approaches for the identification of influential users. It is hoped that the results can stimulate and guide future research.     

Crisis Leadership by Mayors: A Qualitative Content Analysis of Newspapers and Social Media on the MH17 Disaster

Malaysia Airlines Flight MH17 crashed in the Ukraine on 17 July 2014 with 193 Dutch passengers on board. The present study assessed which MH17‐related activities (or absence of certain activities) of 54 mayors from the Netherlands were mentioned in (social) media and if and how they were evaluated. Analyses of newspaper articles and social media showed that public ‘meaning making’ and ‘remembering’ by mayors can be considered as a table stake or conditio sine qua non. Mayors are expected to speak at memorials and attend community activities. Strong appreciation was however retrieved from victims’ families whenever mayors visited them with a listening ear in the privacy of their homes, demonstrating the role mayors can fulfil as mourners‐in‐chief in local communities.     

Administrator-users contribute more to online communities

Lack of user participation and contribution has been a long-standing problem for online communities. We proposed and examined new strategies for cultivating opinion leadership and enabling users to post articles outside of the community theme. We used social role theory to propose that online communities should encourage highly committed users to take administrator roles, which will increase their opinion leadership and contributions to both public spaces and their own user-controlled spaces. We collected multiple-wave and multiple-source data from 1,115 users of a large online community. The results indicate that encouraging users to take administrator roles increases their community contributions.     

Designing and evaluating driver support systems with the user in mind

In this editorial to the special issue we first introduce the field of driver support system (DSS) design and evaluation, frame it into the larger context of human–computer interaction research, and highlight some of its specificities. We then proceed to briefly present the selection of articles that compose this issue. Finally, we put the contributions to the special issue into perspective along a number of dimensions to show how they represent the diversity of current DSS research.