Skip to main content

Über dieses Buch

This book constitutes selected papers from the lectures given at the workshops held in conjunction with the User Modeling, Adaptation and Personalization Conference, UMAP 2011, Girona, Spain, in July 2011. The 40 papers presented were carefully reviewed and selected for inclusion in this book. For each workshop there is an overview paper summarizing the workshop themes, the accepted contributions and the future research trends. In addition the volume presents a selection of the best poster papers of UMAP 2011. The workshops included are: AST, adaptive support for team collaboration; AUM, augmenting user models with real worlds experiences to enhance personalization and adaptation; DEMRA, decision making and recommendation acceptance issues in recommender systems; PALE, personalization approaches in learning environments; SASWeb, semantic adaptive social web; TRUM, trust, reputation and user modeling; UMADR, user modeling and adaptation for daily routines: providing assistance to people with special and specific needs; UMMS, user models for motivational systems: the affective and the rational routes to persuasion.



ASTC: Adaptive Support for Team Collaboration

Adaptive Support for Team Collaboration

The International Workshop on Adaptive Support for Team Collaboration (ASTC 2011) [1] was held in conjunction with the International Conference on User Modeling, Adaptation, and Personalization (UMAP2011), Girona, Spain, July 15, 2011. It was organized with the aim to bring together researchers from different scientific fields and research communities to exchange experiences on how collaboration within teams can be supported through the employment of adaptivity that is grounded on the characteristics of the teams and their individual members, their activities and social bonds.

Alexandros Paramythis, Lydia Lau, Stavros Demetriadis, Manolis Tzagarakis, Styliani Kleanthous

A Visualization Model Supporting an Efficient Context Resumption in Collaboration Environments

Activity awareness support is a key feature for helping people to resume the state of their collaborations when switching among different tasks.

This paper proposes a visualization model supporting an incremental access to information, from an overview of the state of the user’s activity contexts to the details about the events occurred in each of them. The higher visualization layer is represented as a tag cloud and provides a general view of the degree of activity occurred in each context. The other levels are projections on the event history focused on specific perspectives; e.g., general collaboration, task or actor.

A user study showed that our visualization model outperforms standard awareness spaces which provide a direct access to awareness events because it enables users to retrieve the relevant information quicker and more precisely.

Liliana Ardissono, Gianni Bosio, Marino Segnan

Scaffolding Collaborative Learning Opportunities: Integrating Microworld Use and Argumentation

This paper presents our research efforts to support students’ collaborative process when learning mathematics and science as they interact with microworlds and engage in discussions and structured arguments. The system provides students with an environment to explore challenging problems and encourages them to collaborate using a discussion tool to argue and share their rationales and insights using specific examples from microworlds. The challenge of providing useful analysis in such a situation is to recognize, across the learning environment as a whole (both microworld and discussion tool), situations where students need support, and then to make the learners aware of these situations in a productive manner. We present a use case that demonstrates how students work within the system and how we envision the system will provide support. We conclude that the analysis and support that we propose has the potential to enhance the benefits of a combined system and offer more support than a system focused on the individual tools separately.

Toby Dragon, Bruce M. McLaren, Manolis Mavrikis, Eirini Geraniou

AUM: Augmenting User Models with Real World Experiences to Enhance Personalization and Adaptation

Augmenting User Models with Real World Experiences to Enhance Personalization and Adaptation

Digital traces become an important source of information in our physical world. At the same time, these digital traces often represent our real-world activities. Augmented user modeling is an emerging strand of research that aims to connect and exploit activities and events in the digital, social and physical worlds.

Fabian Abel, Vania Dimitrova, Eelco Herder, Geert-Jan Houben

The Personal Adaptive In-Car HMI: Integration of External Applications for Personalized Use

We describe an approach for integrating non-automotive applications into in-car-entertainment systems while taking account of manifold personalization capabilities within a mobile environment. Adaptive user interfaces are generated for external applications using well-known interaction and personalization concepts. The interaction concepts are defined via state-based interaction models and utilized for the integration of various applications in order to guarantee a common look and feel. Context-aware adaptations of the user interfaces are achieved by supporting the process of gathering an augmented user model with a personalization concept in the form of personalization guidelines. We present and discuss an exemplary application for a personalized, safe in-car HMI that automatically adapts to the targeted design and interaction concept as well as to the personal needs of the user within a certain location.

Sandro Rodriguez Garzon, Mark Poguntke

Core Aspects of Affective Metacognitive User Models

As user modelling moves away from a tightly integrated adjunct of adaptive systems and into user modelling service provision, it is important to consider what facets or characteristics of a user might need to be contained within a user model in order to support cognitive functions. Here we examine previous mechanisms for creating a metacognitive and affective user model. We then take first steps to describe the necessary characteristics of a user model we envisage being utilised by an affective metacognitive modelling service and make some suggestion for the source, form and content of such characteristics.

Adam Moore, Victoria Macarthur, Owen Conlan

Recommender Systems and the Social Web

In the past, classic recommender systems relied solely on the user models they were able to construct by themselves and suffered from the “cold start” problem. Recent decade advances, among them internet connectivity and data sharing, now enable them to bootstrap their user models from external sources such as user modeling servers or other recommender systems. However, this approach has only been demonstrated by research prototypes. Recent developments have brought a new source for bootstrapping recommender systems: social web services. The variety of social web services, each with its unique user model characteristics, could aid bootstrapping recommender systems in different ways. In this paper we propose a mapping of how each of the classical user modeling approaches can benefit from nowadays active services’ user models, and also supply an example of a possible application.

Amit Tiroshi, Tsvi Kuflik, Judy Kay, Bob Kummerfeld

Identifying Relevant YouTube Comments to Derive Socially Augmented User Models: A Semantically Enriched Machine Learning Approach

Media resources in social Web spaces trigger social interactions, as they consist of motivating means to create and exchange user-generated content. The massive social content could provide rich resources towards deriving social profiles to augment user models and improve adaptation in simulated learning environments. However, potentially valuable social contributions can be buried within highly noisy content that is irrelevant or spam. This paper sketches a research roadmap toward augmenting user models with key user characteristics derived from social content. It then focuses on the first step: identifying relevant content to create data corpus about a specific activity. A novel, semantically enriched machine learning approach to filter out the noisy content from social media is described. An application on public comments in YouTube on job interview videos has been made to evaluate the approach. Evaluation results, which illustrate the ability of the approach to filter noise and identify relevant social media content, are analysed.

Ahmad Ammari, Vania Dimitrova, Dimoklis Despotakis

DEMRA: Decision Making and Recommendation Acceptance Issues in Recommender Systems

Decision Making and Recommendation Acceptance Issues in Recommender Systems

Recommender Systems (RSs) are software tools and techniques providing suggestions for items to be of use to a user [1]. They exploit adaptive and intelligent systems technologies and have already proved to be valuable for coping with the information overload problem in several application domains. However, while most of the previous research has focused on recommendation techniques and algorithms, i.e., how to compute precise and accurate recommendations, only few studies have stood from users’ angles to consider the processes and issues related to the actual acceptance of the recommendations. Hence, characterizing and evaluating the quality of users’ experience and their subjective attitudes toward the recommendations and the recommendation technologies is an important issue that merits the attention of researchers and practitioners. These issues are important and should be studied both by web technology experts and in the human factor field. The main goal of the first workshop on Decision Making and Recommendation Acceptance issues in Recommender Systems (DEMRA) held at UMAP 2011 was to stimulate the discussion around problems, challenges and research directions about the acceptance of recommendation technologies [2].

Francesco Ricci, Giovanni Semeraro, Marco de Gemmis, Pasquale Lops

Designing an Explanation Interface for Proactive Recommendations in Automotive Scenarios

Recommender techniques are commonly applied to ease the selection process of items and support decision making. Typically, recommender systems are used in contexts where users focus their full attention to the system. This is not the case in automotive scenarios such as gas station recommendation. We want to provide recommendations proactively to reduce driver distraction while searching for information. Proactively delivered recommendations may not be accepted, if the driver does not understand why something was recommended to her. Therefore, our goal in this paper is to enhance transparency of proactively delivered recommendations by means of explanations. We focus on explaining items to convince the user of the relevance of the items and to enable an efficient item selection during driving. We describe a method based on knowledge- and utility-based recommender systems to extract explanations automatically. Our evaluation shows that explanations enable fast decision making for items with reduced information provided to the user. We also show the design of the system in an in-car navigation system.

Roland Bader, Wolfgang Woerndl, Andreas Karitnig, Gerhard Leitner

Group Decision Support for Requirements Negotiation

Requirements engineering is one of the most critical phases in software development. Requirements verbalize decision alternatives that are negotiated by stakeholders. In this paper we present the results of an empirical analysis of the effects of applying group recommendation technologies to requirements negotiation. This analysis has been conducted within the scope of software development projects at our university where development teams were supported with group recommendation technologies when deciding which requirements should be implemented. A major result of the study is that group recommendation technologies can improve the perceived usability (in certain cases) and the perceived quality of decision support. Furthermore, it is not recommended to disclose preferences of individual group members at the beginning of a decision process – this could lead to an insufficient exchange of decision-relevant information.

Alexander Felfernig, Christoph Zehentner, Gerald Ninaus, Harald Grabner, Walid Maalej, Dennis Pagano, Leopold Weninger, Florian Reinfrank

PALE: Personalization Approaches in Learning Environments

Personalization Approaches in Learning Environments

Personalization approaches in learning environments can be addressed from different and complementary perspectives. PALE workshop aimed at the following issues: pedagogic conversational agents, responsive open learning environments, and user modeling for all. Hereby, we report the state of the art in this area as gathered in the workshop papers and comment on the future research directions as discussed during the sessions.

Olga C. Santos, Milos Kravcik, Diana Pérez-Marín

A Procedure to Automatically Adapt Questions in Student – Pedagogic Conversational Agent Dialogues

Pedagogic Conversational Agents are computer applications able to interact with the students in natural language. The agents can keep a student model and adapt the dialogue to the student features. In particular, we propose a procedure to adapt the questions of the agents to the learning style and personality of the students. It is our hypothesis that the students will perceive the adaptation in the dialogue and the questions will be better understood. The procedure has been applied to a group of 20 students (10 Computer Science students and 10 non Computer Science students) and the results provide evidence to support the hypothesis.

Alberto Redondo-Hernández, Diana Pérez-Marín

Modelling Empathy in Social Robotic Companions

Empathy can be broadly defined as the ability to understand and respond appropriately to the affective states of others. In this paper, we present a scenario where a social robot acts as a chess companion for children, and describe our current efforts towards endowing such robot with empathic capabilities. A multimodal framework for modeling some of the user’s affective states that combines visual and task-related features is presented. Using this model of the user, we personalise the learning environment by adapting the robot’s empathic responses to the particular preferences of the child who is interacting with the robot. We also describe a preliminary study conducted in this scenario.

Iolanda Leite, André Pereira, Ginevra Castellano, Samuel Mascarenhas, Carlos Martinho, Ana Paiva

Understanding Student Attention to Adaptive Hints with Eye-Tracking

Prime Climb is an educational game that provides individualized support for learning number factorization skills. This support is delivered by a pedagogical agent in the form of hints based on a model of student learning. Previous studies with Prime Climb indicated that students may not always be paying attentions to the hints, even when they are justified. In this paper we discuss preliminary work on using eye tracking data on user attention patterns to better understand if and how students process the agent’s personalized hints, with the long term goal of making hint delivery more effective.

Mary Muir, Cristina Conati

Psycho-pedagogical Mash-Up Design for Personalising the Learning Environment

The purpose of this paper is to support the creation of a Personalised Learning Environment (PLE) in a psycho-pedagogical sound way. In our approach a PLE is a mash-up of widgets, small tools, which are arranged together. In order to support the compilation of the individual learning environment, educational components have been identified, which might influence the perception of mash-up designs form a learners’ point of view. These identified educational components are the basis to link widgets to psycho-pedagogical information, such as learning strategies and techniques or competences of a learner. Different guidelines have been derived to support learners or tutors to mash-up a PLE with different widgets. Implementation and evaluation approaches are introduced regarding the usefulness and effectiveness of the presented guidelines.

Marcel Berthold, Pablo Lachmann, Alexander Nussbaumer, Sergei Pachtchenko, Andreas Kiefel, Dietrich Albert

SASWeb: Semantic Adaptive Social Web

Semantic Adaptive Social Web


Social Web

, or the so called Web 2.0, is growing daily by the number of users and applications. In this way, a significant part of newly generated Web content and traffic is created by the users itself. They create, connect, comment, tag, rate, remix, upload, download, new or existing resources in an architecture of participation, where user contribution and interaction adds value. Users are also involved in a broad range of social activities like creating social relationships, recommending and sharing resources with friends, creating groups and communities, commenting friends activities and profiles and so on. But not only users benefit from the user-generated content, also social applications profit from that content by using it for personalization and adaptation to user needs.

Federica Cena, Antonina Dattolo, Ernesto William De Luca, Pasquale Lops, Till Plumbaum, Julita Vassileva

Semantic Disambiguation and Contextualisation of Social Tags

We present an algorithmic framework to accurately and efficiently identify the semantic meanings and contexts of social tags within a particular folksonomy. The framework is used for building contextualised tag-based user and item profiles. We also present its implementation in a system called cTag, with which we preliminary analyse semantic meanings and contexts of tags belonging to Delicious and MovieLens folksonomies. The analysis includes a comparison between semantic similarities obtained for pairs of tags in Delicious folksonomy, and their semantic distances in the whole Web, according to co-occurrence based metrics computed with results of a Web search engine.

Ignacio Fernández-Tobías, Iván Cantador, Alejandro Bellogín

Folkview: A Multi-agent System Approach to Modeling Folksonomies

Folksonomies contain semantic information on data, and represent a meaningful mean for identifying similarities among users, resources and tags. Their strong potential is often reduced by the lack in social tagging systems of specialized functionalities for managing and modifying them, and of specific tools for generating customized and dynamic views on them.

The aim of this paper is to present Folkview, an innovative way to conceive a folksonomy in terms of a multi-agent system. Each element (tag, user, resource) become an active entity and the folksonomy transforms itself from a traditional passive container of data into a computational agent, provided of a set of procedural and distributed skills.

The agents actively collaborate in order to generate dynamic and customized views and supporting users in the updating, managing and modifying her personomy, and the same folksonomy.

Antonina Dattolo, Emanuela Pitassi

Selective Propagation of Social Data in Decentralized Online Social Network

In Online Social Networks (OSNs) users are overwhelmed with huge amount of social data, most of which are irrelevant to their interest. Due to the fact that most current OSNs are centralized, people are forced to share their data with the site, in order to be able to share it with their friends, and thus they lose control over it. Decentralized OSNs provide an alternative by allowing users to maintain control over their data. This paper proposes a decentralized OSN architecture to deal with this problem and an approach for propagation of social data in a decentralized OSN that reduces irrelevant data among users. The approach uses interaction between users to construct relationship model of interest, which acts as a filter later while propagating social data of the same interest group. This paper also presents the design of a simulation to analyze the scalability and rate of system learning (convergence) of the system using the relationship model.

Udeep Tandukar, Julita Vassileva

TRUM: Trust, Reputation and User Modeling

Trust, Reputation and User Modeling

The Trust, Reputation and User Modeling (TRUM) workshop (

) pursued the following objectives:

To bring researchers together from the communities of trust and reputation modeling and user modeling;

To initiate and facilitate discussions on the new trends in trust, reputation and user modeling, and to move the trends forward;

To provide a forum for cutting-age research.

Eleven papers were submitted to the workshop. Each submitted paper was carefully reviewed by at least 3 committee members. Finally, seven papers were accepted, including four full papers (12 pages), 2 short papers (8 pages), and 1 poster paper (3 pages + a poster). These high quality papers provide thoughtful discussions on different issues of trust and reputation modeling. They also touch upon the different aspects of user modeling, reflecting the strong connections between trust / reputation modeling and user modeling. All seven accepted papers were invited the postworkshop proceedings and six of them were submitted.

Julita Vassileva, Jie Zhang

Recommending Services in a Trust-Based Decentralized User Modeling System

Trust and reputation mechanisms are often used in peer-to-peer networks, multi-agent systems and online communities for trust-based interactions among the users. Trust values are used to differentiate among members of the community as well as to recommend a service provider. Although different users have different needs and expectations in different aspects of the service providers, traditional trust-based models do not use trust values on neighbors for judging different aspects of service providers. In this paper, we use a multi-faceted trust model where each agent has two sets of trust values: i) trust on different aspects of the quality of service providers, ii) trust on recommendations provided for these aspects. These trust models are used in a decentralized user modeling system where agents have different preference weights in three different criteria of service providers. We have done a simulation of this system that recommends the best possible service provider for each agent according to its preference model. To the best of our knowledge this is the first system that uses multi-faceted trust values both on the qualities of service-providers and on other users’ ability to evaluate these qualities of service providers in a decentralized user modeling system.

Sabrina Nusrat, Julita Vassileva

Building Trust Communities Using Social Trust

The growing popularity of Web based social networks has given rise to the need to build

trust communities

that inspire members to share their experiences, feelings and opinions in an open and honest way. In this paper, we propose a framework for building trust communities in social networks using

social trust

. We first introduce the concept of social trust and social capital, and describe the role they play in building trust communities. We then define a

social trust model

for social networks and the corresponding

recommender system

for building trust communities in social networks. The novel idea behind our social trust model is that we introduce the concept of

engagement trust

and combine it with

popularity trust

to derive a

social trust

of the community as well as of individual members in the community.

Surya Nepal, Wanita Sherchan, Cecile Paris

Improving Access Control for Mobile Consumers of Services by Use of Context and Trust within the Call-Stack

Access control is a key issue in the deployment of systems within corporations. To comply with legal and business requirements and to prevent unauthorized access, the identification and authentication of all users is required. This is typically achieved by using an access control system that performs the identification & authentication of each user at the point of entry into the system. However, as the systems evolve and thus become more complex it is difficult to ensure reliable access control, especially if they are accessed via mobile devices. This paper focuses on improving the existing access control approach for service-oriented systems by applying the concept of device comfort to service providers. Similar to the concept of device comfort, service providers are empowered to decide if they feel comfortable with requests sent to them. This paper presents and evaluates the idea of integrating trust evaluations into service-oriented systems by requiring each service provider to evaluate the trustworthiness of requests and to share their evaluations as part of the call-context within the call-stack.

Min Luo, Ralph Deters

The Influence of Interaction Attributes on Trust in Virtual Communities

In virtual communities (


, forums, blogs), modeling the trust of community members is an effective way to help members make decisions about whose information is more valuable. Towards this goal, we first formulate hypotheses on how various interaction attributes influence trust in virtual communities, and validate these hypotheses through experiments on real data. The influential attributes are then used to develop a trust ranking-based recommendation model called TruRank for recommending the most trustworthy community members. Contrary to traditional recommender systems that rely heavily on subjective manual feedback, our model is built on the foundation of carefully verified objective interaction attributes in virtual communities.

Lizi Zhang, Cheun Pin Tan, Siyi Li, Hui Fang, Pramodh Rai, Yao Chen, Rohit Luthra, Wee Keong Ng, Jie Zhang

Decision Making and Recommendation Protocol Based on Trust for Multi-agent Systems

Agent decision making in large scale multi-agent systems requires techniques which often involve uncertainty and risk. In this paper we propose the decision making protocol based on trust concept with respecting multi-context property of trust. One of the parts of this proposal is a recommendation protocol, which is used for obtaining recommendations from third party agents and gathering information for building trust.

Ondřej Malačka, Jan Samek, František Zbořil, František Vítězslav Zbořil

Handling Subjective User Feedback for Reputation Computation in Virtual Reality

As the interest in virtual reality is growing both from academia and industry, its new application areas emerge, one of which is the virtual marketplaces. We have previously proposed that buyers may share their experience with sellers in virtual marketplaces by exchanging their feedback. The feedback is composed of terms describing merchandise based on the users’ five senses. However, some of these terms (e.g.,


) may be subjective and have different semantics for different buyers. Thus, alignment of the feedback containing subjective terms becomes an indispensable step before using exchanged feedback for reputation computations. In this paper, we propose a novel approach to align subjectivity in user feedback for reputation computation in virtual marketplaces. We demonstrate how sensory data in virtual reality can be exploited to handle subjectivity and describe how the aligned feedback can be used in seller reputation computation.

Hui Fang, Murat Şensoy, Jie Zhang, Nadia Magnenat Thalmann

UMADR: User Modeling and Adaptation for Daily Routines: Providing Assistance to People with Special and Specific Needs

User Modeling and Adaptation for Daily Routines: Providing Assistance to People with Special and Specific Needs

This paper presents a summary of the main contributions to the 2


International Workshop on User Modeling and Adaptation for Daily Routines: Providing Assistance to People with Special and Specific Needs, held in conjunction with UMAP’2011. It describes the discussions carried out during the workshop as well, and includes some reflections about key issues and current trends in the research of user modeling and adaptive systems focused on assisting people with special and specific needs.

Estefanía Martín, Pablo Haya, Rosa M. Carro

Guiding Patients in the Hospital

Automated patient guidance in a hospital can be a helpful service for outpatients. In fact, they often need to move independently to reach locations where medical cares are provided. The provision of such a guidance service motivated the development of


, a mobile advisory system for patients. A live user experiment of the first version of


revealed some shortcomings that stimulated the design of a new improved version that is illustrated in this paper. The new system focus on the exploitation of a workflow management system and on the usage of multiple and distributed user interfaces.

Floriano Zini, Francesco Ricci

Supportive Adaptive User Interfaces Inside and Outside the Home

This paper describes the extension of a previously developed architecture for an Ambient Assisted Living (AAL) environment, called AmbienNet, to provide access to ubiquitous services. The former AAL system generates adaptive instructions to support elderly people at home. This extension includes an adaptive model-based user interface generator that was created for ubiquitous applications. This approach involves the extension of the supportive user interface from home supervision and support to allow access to ubiquitous applications outside the home. The present challenge is how to include adaptive supportive instructions for accessing ubiquitous services outside the home that are coherent with the previously designed home support system.

Raúl Miñón, Julio Abascal

UMMS: User Modelling for Motivational Systems: The Affective and the Rational Routes to Persuasion

User Models for Motivational Systems

The Affective and the Rational Routes to Persuasion

The idea that a computer system could be used to motivate people to perform a certain task on the basis of a user model is certainly not novel. As early as the 80s, intelligent tutoring systems would encourage students to learn by means of tailored feedback and hints [24], and in the 90s patient education systems would attempt to address the problem of compliance to a medical regimen by means of information and personalised advice [1] or would encourage people to adopt healthier lifestyles [19]. It is however only recently that a number of, seemingly non correlated, extensive research efforts, from various perspectives, have started to focus on a more complex cognitive model of rational and extra-rational features, involving emotions, persuasion, motivation and argumentation. We can distinguish three parallel strands of research that have become prominent.

Floriana Grasso, Jaap Ham, Judith Masthoff

Impact of Implicit and Explicit Affective Labeling on a Recommender System’s Performance

Affective labeling of multimedia content can be useful in recommender systems. In this paper we compare the effect of implicit and explicit affective labeling in an image recommender system. The implicit affective labeling method is based on an emotion detection technique that takes as input the video sequences of the users’ facial expressions. It extracts Gabor low level features from the video frames and employs a kNN machine learning technique to generate affective labels in the valence-arousal-dominance space. We performed a comparative study of the performance of a content-based recommender (CBR) system for images that uses three types of metadata to model the users and the items: (i) generic metadata, (ii) explicitly acquired affective labels and (iii) implicitly acquired affective labels with the proposed methodology. The results showed that the CBR performs best when explicit labels are used. However, implicitly acquired labels yield a significantly better performance of the CBR than generic metadata while being an unobtrusive feedback tool.

Marko Tkalčič, Ante Odić, Andrej Košir, Jurij Franc Tasič

Arguing about Emotion

Emotions are commonly thought to be beyond rational analysis. In this paper, we develop the position that emotions can be the


of argumentation and used as terms in

emotional argumentation schemes

. Thus, we can argue about whether or not, according to normative standards and available evidence, it is plausible that an individual had a particular emotion. This is particularly salient in legal cases, where decisions can depend on explicit arguments about emotional states.

Martyn Lloyd-Kelly, Adam Wyner

Motivating People in Smart Environments

In this paper we discuss the possibility to extend PORTIA, a persuasion system currently applied in human-agent dialogs, to support ambient persuasion. We have identified a fitness center as an appropriate smart environment in which ambient persuasion strategies can be applied. According to the Ubiquitous Computing vision, in the fitness center the user is surrounded by several connected devices that cooperate in the persuasion process, each of them with the most appropriate strategy, mode of persuasion, style of communication according to the context. To this aim we propose a multi-agent system able to support this distributed and intelligent approach to persuasion that allows to follow the user during the gradual change from the initial attitude to sustain of long term behaviours.

Berardina De Carolis, Irene Mazzotta

Towards Adaptive Recruitment and Engagement Mechanisms in Social Systems

Although successful

online communities

have engaged thousands of users, designers still struggle to recruit newcomers and increase current contribution rates. Related work on encouraging contributions has drawn from Social Psychology, Sociology and Economics theories. Engagement mechanisms embed the principles of these theories, and experimental studies evaluate the impact of different mechanisms on the contribution rates. Significant differences among alternative engagement mechanisms have been found, however, the results are sometimes contradictory for different groups of users. Our hypothesis is that the effectiveness of engagement mechanisms may depend on users’ characteristics, and not solely on the mechanism itself. To start exploring this hypothesis, we performed a study to evaluate the impact of recruitment and engagement messages on different users’ cohorts. Levels of current participation rates and demographic data were analyzed in order to explain differences in the impact of these engagement strategies.

Claudia López, Peter Brusilovsky

Selected Posters

Towards a New Dimension for User Modeling: The Use of Sensory Vocabulary

One aspect of user preference, which is of high interest especially for the field of e-learning, concerns the mode of presenting information: What sensory system(s) should be addressed to make information interesting and easy to understand for the user? The answer might be found when looking at the user’s perceptual preferences. To test the user would be the most direct way – and the most annoying for the user. In our research, we investigate the use of sensory vocabulary in forum texts as a source of implicit information on the user. Therefore, a corpus with more than 1,000,000 forum posts was analyzed for the occurrence of expressions that are directly linked to a sensory system. We found that users differ significantly in their use of sensory expressions and that most users have preferred patterns for the use of sensory expressions.

Gudrun Kellner, Bettina Berendt

SERUM: Collecting Semantic User Behavior for Improved News Recommendations

How can semantic data and semantic technologies be leveraged for personalization and recommendation services? In this paper, we present SERUM (Semantic Recommendations based on large unstructured datasets), a news recommendation system that utilizes semantic technologies to collect implicit user behavior and to build semantic user models. These models, combined with large-scale semantic datasets, are then used to compute personalized news recommendations using graph-based algorithms. We introduce the building blocks of SERUM for the semantic data management, personalization and recommendation, with the main focus on the implicit user behavior collection. Therefore, our system uses RDFa to collect meaningful user behavior and a self-developed user behavior ontology (the User Behavior Ontology, in short UBO) to build semantic user behavior models. The main contribution of this work is the introduction of the UBO and the associated semantic user tracking and modeling process.

Till Plumbaum, Andreas Lommatzsch, Ernesto William De Luca, Sahin Albayrak

INGRID: A Web Service Tool for Hierarchical Open Learner Model Visualization

This paper presents a tool to visualize open learner models. The tool is domain independent and is freely available as a web service. It can be easily integrated with any existing web-based learning environment.

Ricardo Conejo, Monica Trella, Ivan Cruces, Rafael Garcia

An Acceptance Model of Recommender Systems Based on a Large-Scale Internet Survey

Recommendation services capture and exploit personal information such as demographic attributes, preferences, and user behaviors on the internet. It is known that some users feel uneasiness regarding such information acquisition by systems and have concern over their online privacy. Investigating the structure of the uneasiness and evaluating the effect to user acceptance of the recommender systems is an important issue to develop user-accepting services. In this study, we developed an acceptance model of recommender systems based on a large-scale internet survey using 60 kinds of pseudo-services.

Hideki Asoh, Chihiro Ono, Yukiko Habu, Haruo Takasaki, Takeshi Takenaka, Yoichi Motomura


Weitere Informationen