Autor*innen mit den meisten Dokumenten
Auflistung nach:
Neueste Veröffentlichungen
- editorialIntroduction to Special Issue on User-Centred Recommender Systems(i-com: Vol. 14, No. 1, 2015) Gross, Tom; Ziegler, Jürgen; Ziegler, Jürgen
- ZeitschriftenartikelCall for a Holistic Approach to the Use of Social Intranets(i-com: Vol. 14, No. 1, 2015) Kolb, Georg; Ziegler, JürgenThere are high expectations on what social intranets can do for productivity. However, there is still a large gap between promise and delivery, mainly caused by a misunderstanding of the user perspective. Usability of social intranets needs to be redefined in a holistic way, integrating the four dimensions of business, culture, technology and communication. And we need to build this integration into the workflow of social intranet teams by establishing a cross-functional body steering the project.
- ZeitschriftenartikelDeveloping Intranet Strategy: An Interdisciplinary Building Block Model(i-com: Vol. 14, No. 1, 2015) Riemke-Gurzki, Thorsten; Ziegler, JürgenIntranets became the central platform for internal corporate communication, business processes and information technology in the last decade. This huge application scope leads to severe project traps: How can a corporate-wide, interdisciplinary intranet strategy be developed, established and maintained? This article shows the challenges and potential problems for the development of an intranet strategy. It introduces a building block model for intranet strategy. The model includes strategic dimensions as well as cultural aspects and project scope.
- KonferenzbeitragMerging Interactive Information Filtering and Recommender Algorithms – Model and Concept Demonstrator(i-com: Vol. 14, No. 1, 2015) Loepp, Benedikt; Herrmanny, Katja; Ziegler, Jürgen; Ziegler, JürgenTo increase controllability and transparency in recommender systems, recent research has been putting more focus on integrating interactive techniques with recommender algorithms. In this paper, we propose a model of interactive recommending that structures the different interactions users can have with recommender systems. Furthermore, as a novel approach to interactive recommending, we describe a technique that combines faceted information filtering with different algorithmic recommender techniques. We refer to this approach as blended recommending. We also present an interactive movie recommender based on this approach and report on its user-centered design process, in particular an evaluation study in which we compared our system with a standard faceted filtering system. The results indicate a higher level of perceived user control, more detailed preference settings, and better suitability when the search goal is vague.
- ZeitschriftenartikelNo More Battles – User-centric Approaches as Key to Successful Intranets(i-com: Vol. 14, No. 1, 2015) Wagner, Anne Christine; Ziegler, JürgenIn the short history of intranets a lot of IT-centric paradigms have been prevailing (tool choice, architectural questions, overall IT strategy). The emergence of intranet paradigms, referred to as Web2.0, as well as changed user expectations due to consumerization and high adaption of mobile devices challenge the traditionally technology-driven approach in enterprises: Today, users realize that there is more to claim and fight for. This article introduces approaches that start from the practitioner's perspective and help to align users, IT and strategic stakeholders with the purpose of forming an alliance between them and of finding the scope and design that fits all requirements.
- ZeitschriftenartikelNo Success without Purpose(i-com: Vol. 14, No. 1, 2015) Gumm, Dorina; Ziegler, JürgenThe purpose an organisation attaches to its intranet should be the starting point for justifying an intranet project, defining use cases and ultimately being able to measure its success. An intranet's prospects for success are best when it is perceived as a tool for operations management. This is one of the core findings of the “KlinikNet 2.0” project chosen by hospital directors as one of five “IT Key Topics” in 2014.
- ZeitschriftenartikelBlessing or Curse: “Everybody Knows how to Write” – How Can Good Editorial Work Be Accomplished on an Intranet?(i-com: Vol. 14, No. 1, 2015) Häfele, Heike; Ziegler, JürgenIn many companies, employees and managers alike are critical about the quality of their intranet. Solutions focusing on technical and process improvements frequently fail to produce sustainable results because they ignore one key factor for the quality of written content: Amid the day-to-day business routine there are too many obstacles for doing good editorial work and acquiring writing skills. To encourage the production of quality texts, an environment must be created that encourages writing, a culture where editorial work is firmly established, trained and performed efficiently.
- KonferenzbeitragItem Familiarity as a Possible Confounding Factor in User-Centric Recommender Systems Evaluation(i-com: Vol. 14, No. 1, 2015) Jannach, Dietmar; Lerche, Lukas; Jugovac, Michael; Ziegler, JürgenUser studies play an important role in academic research in the field of recommender systems as they allow us to assess quality factors other than the predictive accuracy of the underlying algorithms. User satisfaction is one such factor that is often evaluated in laboratory settings and in many experimental designs one task of the participants is to assess the suitability of the system-generated recommendations. The effort required by the user to make such an assessment can, however, depend on the user’s familiarity with the presented items and directly impact on the reported user satisfaction. In this paper, we report the results of a preliminary recommender systems user study using Mechanical Turk, which indicates that item familiarity is strongly correlated with overall satisfaction.
- KonferenzbeitragOn the Importance of Subtext in Recommender Systems(i-com: Vol. 14, No. 1, 2015) Grasch, Peter; Felfernig, Alexander; Ziegler, JürgenConversational recommender systems have been shown capable of allowing users to navigate even complex and unknown application domains effectively. However, optimizing preference elicitation remains a largely unsolved problem. In this paper we introduce SPEECHREC, a speech-enabled, knowledge-based recommender system, that engages the user in a natural-language dialog, identifying not only purely factual constraints from the users’ input, but also integrating nuanced lexical qualifiers and paralinguistic information into the recommendation strategy. In order to assess the viability of this concept, we present the results of an empirical study where we compare SPEECHREC to a traditional knowledge-based recommender system and show how incorporating more granular user preferences in the recommendation strategy can increase recommendation quality, while reducing median session length by 46 %.
- KonferenzbeitragSupporting Informed Negotiation Processes in Group Recommender Systems(i-com: Vol. 14, No. 1, 2015) Gross, Tom; Ziegler, JürgenGroup recommender systems make suggestions to groups of users who want to share experiences or products. Despite their high potential for helping users, GRS face diverse challenges that can be clustered into two groups: predictions and processes. Generating predictions of the goodness of the fit of recommendations to the group has been seen as a core challenge of recommender systems from their beginning, while supporting the processes of discussion for reaching consensus on the item to pick is a more recent challenge. In this paper I report on a base platform for GRS with powerful algorithms for generating and explaining recommendations with high predictions, and an easy and effective process model for GRS.