Interaction mining and skill-dependent recommendations for multi-objective team composition

Web-based collaboration and virtual environments supported by various Web 2.0 concepts enable the application of numerous monitoring, mining and analysis tools to study human interactions and team formation processes. The composition of an effective team requires a balance between adequate skill fulfillment and sufficient team connectivity. The underlying interaction structure reflects social behavior and relations of individuals and determines to a large degree how well people can be expected to collaborate. In this paper we address an extended team formation problem that does not only require direct interactions to determine team connectivity but additionally uses implicit recommendations of collaboration partners to support even sparsely connected networks. We provide two heuristics based on Genetic Algorithms and Simulated Annealing for discovering efficient team configurations that yield the best trade-off between skill coverage and team connectivity. Our self-adjusting mechanism aims to discover the best combination of direct interactions and recommendations when deriving connectivity. We evaluate our approach based on multiple configurations of a simulated collaboration network that features close resemblance to real world expert networks. We demonstrate that our algorithm successfully identifies efficient team configurations even when removing up to 40% of experts from various social network configurations.     

Research on group awareness of networked collaboration within the design team and between teams

Group awareness is the critical content of collaboration in a networked collaborative design team, and it is a meaningful way to study teamwork efficiency. However, existing methods that describe awareness information are not comprehensive. They all set an ideal collaborative environment of the single role and single activity, ignoring the bidirectional and overlapping of the collaboration process. To meet this gap, a novel group awareness method for the networked collaboration design team is proposed in this paper from the actual collaborative process. Firstly, the awareness information granularity in the joint work of the networked collaborative design team is described in detail, and the group awareness model is established. Then, the intra- and inter-team collaboration of networked collaborative design team is quantified, and correspondingly, combined with the degree of cooperation between members, a method for solving the group awareness ability of intra- and inter-team association by adopting awareness calculation is presented. Last, to illustrate the feasibility of the suggested approach, a vehicle interior collaborative design task is taken as an example. This study can provide practical guidance for a related design service platform to optimize team collaboration efficiency and select team members objectively and fairly.     

一种专家地图构建方法

专家地图是专家个人知识和技能信息及专家协作网络信息的记录。基于图论的方法给出专家发现社会协作网的算法。定义一种从企业局域网的异构数据文档中发现专家地图的任务,给出实现该任务的多种模型,并将模型应用于TRCKMS系统的开发中。在W3C语料库上进行的实验表明,该模型能够提高专家发现的效率。     

Conceptualizing the Awareness of Collaboration: A Qualitative Study of a Global Virtual Team

Innovative organizations are increasing their use of distributed teamwork, but there are several difficulties in reaching shared understanding between the team members in these settings. A lack of awareness of other team members’ working processes is one of the drawbacks that a virtual team may face while attempting to collaborate on a shared task. In this study virtual teamwork was supported with a specific working model. The aim was to investigate virtual team members’ awareness of collaboration. One global team (N=19) within a single organization worked as a distributed team in a shared web-based workspace for three months. The data were gathered by means of questionnaires, log-files of the shared virtual workspace and collected company documents in order to find out how team members perceive their collaboration. Based on qualitative data analysis, three different aspects of collaboration awareness were identified: an awareness of the possibility for collaboration, an awareness of the aims of collaboration, and an awareness of the process of collaboration. The results presented in this paper give guidelines for discussing what the awareness of collaboration means in the context of distributed collaboration.     

Awareness support for asynchronous engineering collaboration

This study addresses collaboration awareness for asynchronous distributed engineering collaboration with computer‐aided design (CAD) browsers. An analysis of the characteristics of asynchronous collaboration identified the information that needs to be presented. Two features for a CAD browser system, team member information enhancement and task information enhancement, were designed to improve collaborator and task awareness. An experiment was conducted to test the effectiveness of the new proposed features. The results of the experiment indicated the following. First, the enhancement of team member information and task information improved collaboration efficiency by 8.1 and 20.2%, respectively. Second, for asynchronous collaboration, the availability and workload of team members need to be presented rather than capturing and presenting dynamic information about team members. Third, the information about the status of each task, such as the progress, time passed, and dependability, needs to be enhanced for efficient collaboration. © 2003 Wiley Periodicals, Inc. Hum Factors Man 13: 97–113, 2003.     

Using hybrid scheduling for the semi-autonomous formation of expert teams

Selecting and scheduling human experts to cooperatively solve a problem can be a highly complex task, given various constraints (such as what expertise is needed and when) and preferences (such as which expertise an expert most prefers to exercise). Computational agents can thus greatly help users form and schedule expert teams. This paper introduces a new formulation of the team formation and scheduling problem as a Hybrid Scheduling Problem (HSP) and compares the performance of an agent using the HSP formulation to a prior agent-based approach. We empirically demonstrate the promise of the HSP formulation and highlight how the application of HSP techniques to this problem has led us to identify important modifications to mechanisms that improve HSP solving. Finally, we summarize how the HSP formulation can support human-agent collaboration during the process of forming and scheduling expert teams.     

Effects of task complexity on individual creativity through knowledge interaction: A comparison of temporary and permanent teams

Using the interactionist’s perspective of creativity, this paper proposes a new research model of creativity manifestation to explore how factors affecting individual creativity depend on team characteristics. We investigated the antecedents of creativity in the literature—task complexity, team member exchange, and knowledge sharing—and then examined the relationships and differences between temporary and permanent teams. To maximize practical implications, we studied two team types like project task force (PTF) and research and development (R&D) teams in the Information and Communication Technology (ICT) industry in Korea, where strong creativity is required for team performance. PTF teams operate with a clear mission to be completed on a deadline, while R&D teams create scientific enhancements for existing products. The proposed structural model was tested empirically with cross-sectional data from 289 professionals from the two team types. Results indicated that, in the case of PTF teams, task complexity had an indirect relationship with individual complexity through knowledge interaction among team members, while for R&D teams, task complexity was directly associated with individual creativity, and indirectly associated with the creativity through team member exchange. Thus, team characteristics must be considered together with task complexity and knowledge interactions in order to achieve team goals more effectively by maximizing each member’s creativity.     

Team formation in social networks based on collective intelligence – an evolutionary approach

The tremendous growth of the social web has inspired research communities to discover social intelligence, which encompasses a wide spectrum of knowledge characterized by human interaction, communication and collaboration, thereby exploiting collective intelligence (CI) to support the successful existence of social communities on the Web. In this work, we address the team formation problem for generalized tasks where a set of experts is to be discovered from an expertise social network that can collaborate effectively to accomplish a given task. The concept of CI that emerges from these collaborations attempts to maximize the potential of the team of experts, rather than only aggregating individual potentials. Because the team formation problem is NP-hard, a genetic algorithm-based approach is applied to optimize computational collective intelligence in web-based social networks. To capture the essence of CI, a novel quantitative measure Collective Intelligence Index (CII) is proposed that takes two factors into account –the “enhanced expertise score” and the “trust-based collaboration score”. This measure relates to the social interactions among experts, reflecting various affiliations that form a network of experts that help to drive creativity by deepening engagements through collaboration and the exchange of ideas and expertise, thereby enriching and enhancing the knowledge base of experts. The presented model also captures the teams’ dynamics by considering trust, which is essential to effective interactions between the experts. The computational experiments are performed on a synthetic dataset that bears close resemblance to real-world expertise networks, and the results clearly establish the effectiveness of our proposed model.     

A set partitioning based goal programming model for the team formation problem

In this paper, we offer a multi-objective set-partitioning formulation for team formation problems using goal programming. Instead of selecting team members to teams, we select suitable teams from a set of teams. This set is generated using a heuristic algorithm that uses the social network of potential team members. We then utilize the proposed multi-objective formulation to select the desired number of teams from this set that meets the skill requirements. Therefore, we ensure that selected teams include individuals with the required skills and effective communication with each other. Two real datasets are used to test the model. The results obtained with the proposed solution are compared with two well-known approaches: weighted and lexicographic goal programming. Results reveal that weighted and lexicographic goal programming approaches generate almost identical solutions for the datasets tested. Our approach, on the other hand, mostly picks teams with lower communication costs. Even in some cases, better solutions are obtained with the proposed approach. Findings show that the developed solution approach is a promising approach to handle team formation problems.     

模糊多目标进化的社会团队形成方法

目前,基于社会网络的团队形成问题研究大多采取0-1规则度量专家技能。针对人们通常使用自然语言描述专家技能的情况,提出模糊多目标进化的社会团队形成方法。该方法研究模糊环境下如何从专家社会网络中查询出合适的个体并组成规模一定的团队,实现最小的通信代价和最优的团队绩效。其采用模糊语言变量代替以0-1规则为代表的精确参数来描述专家技能,使用团队绩效的概念衡量团队对任务P的技能表现力。鉴于标准SPEA2算法在进化初期收敛速度慢的缺点,引入档案精英学习策略生成优良个体。另外,考虑到专家技能的模糊性,文中提出了细粒度Dominance判断作为 判断 个体间支配关系的新准则。仿真实验结果证明,改进算法的收敛速度快,获得的近似Pareto前沿更加逼近真实解集,可有效求解团队形成问题。     

Mixture of feature specified experts

Mixture of Experts is one of the most popular ensemble methods in pattern recognition systems. Although, diversity between the experts is one of the necessary conditions for the success of combining methods, ensemble systems based on Mixture of Experts suffer from the lack of enough diversity among the experts caused by unfavorable initial parameters. In the conventional Mixture of Experts, each expert receives the whole feature space. To increase diversity among the experts, solve the structural issues of Mixture of Experts such as zero coefficient problem, and improve efficiency in the system, we intend to propose a model, entitled Mixture of Feature Specified Experts, in which each expert gets a different subset of the original feature set. To this end, we first select a set of feature subsets which lead to a set of diverse and efficient classifiers. Then the initial parameters are infused to the system with training classifiers on the selected feature subsets. Finally, we train the expert and the gating networks using the learning rule of classical Mixture of Experts to organize collaboration between the members of system and aiding the gating network to find the best partitioning of the problem space. To evaluate our proposed method, we have used six datasets from the UCI repository. In addition the generalization capability of our proposed method is considered on real-world database of EEG based Brain-Computer Interface. The performance of our method is evaluated with various appraisal criteria and significant improvement in recognition rate of our proposed method is indicated in all practical tests.     

工作流管理系统中协同建模技术研究

文中以工作流原型系统－ＡＷＦｌｏｗ为背景,就工作流管理系统中的协同建模过程进行了分析,并在ＡＷＦｌｏｗ中的工作流模型基础上提出了一种基于卡片的工作流表示方法,可以较方便地支持多成员协同建模,另外,还提出了一种支持同步和异步协同工作方式的混合式控制结构,提高了成员间协作的灵活性。     

基于偏序任务的社会网络合作算法研究

针对不同任务之间通常存在偏序关系这种实际情况,提出了基于偏序任务的社会网络合作问题(collaboration problem in social networks based on tasks with partial ordering relations, CSN-TPR).该问题研究如何从社会网络中选择合适的团队来合作完成具有偏序关系的任务集,使得由通信代价、时间代价和预算代价构成的总体代价性能最优.首先证明了CSN-TPR是NP-hard问题,然后利用爬山法、分支限界策略和动态规划方法提出了近似算法HillClimbingTF_BBS.HillClimbingTF_BBS算法不仅输出有效的团队,而且能给出团队成员的具体任务分配以及每项任务的开始时间. 真实数据上的实验结果表明： HillClimbingTF_BBS算法能有效并高效求解CSN-TPR.     

Efficient algorithms for team formation with a leader in social networks

Given a project with a set of required skills, it is an important and challenging problem of find a team of experts that have not only the required skill set but also the minimal communication cost. Furthermore, in view of the benefits of greater leaders, prior work presented the team formation problem with a leader where the leader is responsible for coordinating and managing the project. To find the best leader and the corresponding team, the prior work exhaustively evaluates each candidate and the associated team, incurring substantial computational cost. In this paper, we propose two efficient algorithms, namely the BCPruning algorithm and the SSPruning algorithm, to accelerate the discovery of the best leader and the corresponding team by reducing the search space of team formation for candidates. The BCPruning algorithm aims at selecting better initial leader candidates to obtain lower communication cost, enabling effective candidate pruning. On the other hand, the SSPruning algorithm allows each leader candidate to have a lower bound on the communication cost, leading some candidates to be safely pruned without any computation. Besides, the SSPruning algorithm exploits the exchanged information among experts to aid initial candidate selection as well as team member search. For performance evaluation, we conduct experiments using a real dataset. The experimental results show that the proposed BCPruning and SSPruning algorithms are respectively 1.42–1.68 and 2.64–3.25 times faster than the prior work. Moreover, the results indicate that the proposed algorithms are more scalable than the prior work.     

Practice and carryover effects when using small interaction devices

The use of interaction devices in modern work often challenges the human motor system, especially when these devices introduce unfamiliar transformations to the user. In this paper we evaluated expert performance and skill differences between experts and novices when using small motion- and force-controlled interaction devices (touchpad and mini-joystick) in an applied text-editing task. Firstly, experts performed better with their familiar input device than with an unfamiliar one. Particularly touchpad experts operating the unfamiliar mini-joystick showed highly asymmetric carryover costs. Results showed that the efficient performance of experts depended on domain-specific skills, which were not transferable. Secondly, with considerable practice (more than observed for simple and short tasks) novices were brought up to higher levels of performance. The motion-transformation between hand and cursor action was easier in understanding and application than the force-transformation. Thus, the touchpad was used more efficiently than the mini-joystick. In conclusion, practice effects found so far are considerably underestimated when it comes to an applied task. The results give reason to develop and implement skill-sensitive training procedures, since the acquisition of domain-specific skills is critical for expert performance. As a consequence, training procedures might be essential for complex applications and/or unfamiliar device transformations.     

Team leader strategies for enabling collaboration technology adaptation: team technology knowledge to improve globally distributed systems development work

Active management of team adaptation of collaboration technologies offers an important lever for influencing success rates in distributed project work, particularly in settings characterized by high task interdependence, such as information systems development (ISD). Substantial uncertainty exists as to how a leader might influence such technology adaptation during project work. Prior research indicates that a major leader resource to accomplish technology adaptation in these settings would be team technology knowledge (TTK). This empirical field study develops a five-factor model of strategies regarding awareness of TTK that team leaders take in intervening to affect technology adaptation in distributed ISD projects. The analysis indicates insights into when and why these strategies are effective and how they relate to each other as well as the leader's awareness of TTK. The study provides a way for ISD team leaders to approach improving team collaboration from a socio-technical perspective as well as insights into potential levers for improving team technology adaptation and the efficacy of ISD projects.     

Information Alignment and Task Coordination in Organizations: An 'Information Clutch' Metaphor

Despite their rising popularity, distributed teams face a number of collaboration challenges that may potentially hinder their ability to productively coordinate their resources, activities, and information, often in dynamic and uncertain task environments. In this paper, we focus principally on the criticality of information alignment for supporting coordinated task performance in complex operational environments. As organizations become more expertise, geographically, and temporally distributed, appropriate alignment and coordination among distributed team members becomes more critical for minimizing the occurrence of information flow failures, poor decision-making, and degraded team performance. We first describe these coordination processes using the metaphor of an 'information clutch' that allows for smooth transitions of task priorities and activities in expert teams. We then present two case study examples that illustrate the potentially significant impact of information sharing and information alignment on productivity and coordination in organizations. We conclude with a discussion of future directions in this area.     

Information Alignment and Task Coordination in Organizations: An ‘Information Clutch’ Metaphor

Abstract

Despite their rising popularity, distributed teams face a number of collaboration challenges that may potentially hinder their ability to productively coordinate their resources, activities, and information, often in dynamic and uncertain task environments. In this paper, we focus principally on the criticality of information alignment for supporting coordinated task performance in complex operational environments. As organizations become more expertise, geographically, and temporally distributed, appropriate alignment and coordination among distributed team members becomes more critical for minimizing the occurrence of information flow failures, poor decision-making, and degraded team performance. We first describe these coordination processes using the metaphor of an ‘information clutch’ that allows for smooth transitions of task priorities and activities in expert teams. We then present two case study examples that illustrate the potentially significant impact of information sharing and information alignment on productivity and coordination in organizations. We conclude with a discussion of future directions in this area.     

Using Project-Based-Learning in a mobile application development course—An experience report

In this paper, we report the experience gained in a Mobile Application Development course. We involved students in Computer Science at the University of Salerno, who in teams had to conduct a project. The goal of this project was to design and develop applications (or simply app) for Android-based devices. The adopted teaching approach was based on Project-Based-Learning and enhanced collaboration and competition. Collaboration took place among members of the same team (intra-team), while competition among different teams of students (extra-team). To allow intra-team collaboration, students used GitHub as Computer-Supported-Collaborative-Learning tool. It provided support for implicit and explicit communication among members in each team and for distributed revision control and management of software artifacts (e.g., source code and requirements models). Developed apps underwent a final public competition prized by IT managers of national and international software companies. This is how we implemented extra-team competition. IT managers expressed a positive judgment on both students׳ competition and developed apps. Also, students provided very good feedback on used teaching approach and support GitHub provided.     

Social skills as predictors of communication,performance and quality of collaboration in project‐based learning

The assumption that social skills are necessary ingredients of collaborative learning is well established but rarely empirically tested. In addition, most theories on collaborative learning focus on social skills only at the personal level, while the social skill configurations within a learning group might be of equal importance. Using the integrative framework, this study investigates which social skills at the personal level and at the group level are predictive of task‐related e‐mail communication, satisfaction with performance and perceived quality of collaboration. Data collection took place in a technology‐enhanced long‐term project‐based learning setting for pre‐service teachers. For data collection, two questionnaires were used, one at the beginning and one at the end of the learning cycle which lasted 3 months. During the project phase, the e‐mail communication between group members was captured as well. The investigation of 60 project groups (N = 155 for the questionnaires; group size: two or three students) and 33 groups for the e‐mail communication (N = 83) revealed that personal social skills played only a minor role compared to group level configurations of social skills in predicting satisfaction with performance, perceived quality of collaboration and communication behaviour. Members from groups that showed a high and/or homogeneous configuration of specific social skills (e.g., cooperation/compromising, leadership) usually were more satisfied and saw their group as more efficient than members from groups with a low and/or heterogeneous configuration of skills.