10 Personalization approaches for remote collaborative interaction
-
Chiara Luisa Schleu
Abstract
In the past years, work settings became more flexible, involving a drastically increased share of remote work and collaboration. Remote collaborative interaction where teams might not only be spatially distributed but also involve highly diverse members with different interests, backgrounds and attitudes, require elaborated system support to turn out successful for the team. In the domain of computer-supported cooperative work, there exist numerous approaches that can be used by systems to support collaborative interaction, such as communication and coordination tools, awareness mechanisms or sharing options. Although rich in functionality, out-of-the-box solutions are often not able to adapt to individual needs of the people in a team and specific needs of a team as a whole. Many related challenges can be attempted to be overcome by means of personalization, either user-driven or system-driven, based on either the explicit collection of user requirements or on the automated interpretation of interaction data. Yet, personalized support often does not consider the specific ad hoc situations a team might be in. Thus, in this chapter, we discuss a phenomenological approach, driven by identification and analysis of particular, potentially critical team situations, combined with traditional personalization concepts. We present a qualitative interview study with seven experts of different related fields who were asked to suggest personalization approaches for selected team situations in a remote collaboration setting. The exemplary team situations were derived from a prestudy data elicitation with a team of four persons interacting on a collaborative task. Experts’ statements were thematically coded, categorized and compiled to a taxonomy of personalized collaboration support measures. Further, we derive design implications for personalized collaborative systems based on this taxonomy.
Abstract
In the past years, work settings became more flexible, involving a drastically increased share of remote work and collaboration. Remote collaborative interaction where teams might not only be spatially distributed but also involve highly diverse members with different interests, backgrounds and attitudes, require elaborated system support to turn out successful for the team. In the domain of computer-supported cooperative work, there exist numerous approaches that can be used by systems to support collaborative interaction, such as communication and coordination tools, awareness mechanisms or sharing options. Although rich in functionality, out-of-the-box solutions are often not able to adapt to individual needs of the people in a team and specific needs of a team as a whole. Many related challenges can be attempted to be overcome by means of personalization, either user-driven or system-driven, based on either the explicit collection of user requirements or on the automated interpretation of interaction data. Yet, personalized support often does not consider the specific ad hoc situations a team might be in. Thus, in this chapter, we discuss a phenomenological approach, driven by identification and analysis of particular, potentially critical team situations, combined with traditional personalization concepts. We present a qualitative interview study with seven experts of different related fields who were asked to suggest personalization approaches for selected team situations in a remote collaboration setting. The exemplary team situations were derived from a prestudy data elicitation with a team of four persons interacting on a collaborative task. Experts’ statements were thematically coded, categorized and compiled to a taxonomy of personalized collaboration support measures. Further, we derive design implications for personalized collaborative systems based on this taxonomy.
Chapters in this book
- Frontmatter I
- Introduction V
- Contents IX
- List of Contributing Authors XI
-
Part I: Foundations of personalization
- 1 Theory-grounded user modeling for personalized HCI 1
- 2 User-centered recommender systems 33
- 3 Fairness of information access systems 59
-
Part II: User input and feedback
- 4 Personalization and user modeling for interaction processes 81
- 5 How to use socio-emotional signals for adaptive training 99
- 6 Explanations and user control in recommender systems 129
- 7 Feedback loops and mutual reinforcement in personalized interaction 153
-
Part III: Personalization purposes and goals
- 8 Personalizing the user interface for people with disabilities 175
- 9 Personalized persuasion for behavior change 205
- 10 Personalization approaches for remote collaborative interaction 237
-
Part IV: Personalization domains
- 11 Listener awareness in music recommender systems: directions and current trends 279
- 12 Tourist trip recommendations – foundations, state of the art and challenges 313
- 13 Pictures as a tool for matching tourist preferences with destinations 337
- Index 355
Chapters in this book
- Frontmatter I
- Introduction V
- Contents IX
- List of Contributing Authors XI
-
Part I: Foundations of personalization
- 1 Theory-grounded user modeling for personalized HCI 1
- 2 User-centered recommender systems 33
- 3 Fairness of information access systems 59
-
Part II: User input and feedback
- 4 Personalization and user modeling for interaction processes 81
- 5 How to use socio-emotional signals for adaptive training 99
- 6 Explanations and user control in recommender systems 129
- 7 Feedback loops and mutual reinforcement in personalized interaction 153
-
Part III: Personalization purposes and goals
- 8 Personalizing the user interface for people with disabilities 175
- 9 Personalized persuasion for behavior change 205
- 10 Personalization approaches for remote collaborative interaction 237
-
Part IV: Personalization domains
- 11 Listener awareness in music recommender systems: directions and current trends 279
- 12 Tourist trip recommendations – foundations, state of the art and challenges 313
- 13 Pictures as a tool for matching tourist preferences with destinations 337
- Index 355
