Triggers and connection-making for serendipity via user interface in recommender systems
| Autor: | Ahmad Hassan Afridi, Fatma Outay |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Computer science
Serendipity Sentiment analysis Mobile computing 020206 networking & telecommunications 02 engineering and technology Transparency (human–computer interaction) Management Science and Operations Research Recommender system Computer Science Applications User interface design Interactivity Hardware and Architecture Human–computer interaction 020204 information systems 0202 electrical engineering electronic engineering information engineering User interface |
| Zdroj: | Personal and Ubiquitous Computing. 25:77-92 |
| ISSN: | 1617-4917 1617-4909 |
| Popis: | This paper reports on the use of transparency in recommender a system that facilitates serendipitous encounters for users. Currently, there are serendipitous recommender systems that facilitate serendipitous encounters; however, there are no studies on the connection-making process or on the process of achieving connection-making through a user interface design. Adding to our previous work on connection-making and serendipity-facilitating recommender systems, we examine transparency in recommender systems as it relates to connection-making we studied transparency of recommendations to foster connection-making. This study is novel as it introduces a new user interface design for recommender system in academia and new study methods and approaches and studies a large group of users who are using this recommender system. The user interface components such as bubble messages on recommender system mechanism, user controls on manipulating the recommender system outcomes and showing authors work addition to recommendation. Repeated measure design of research was used to study serendipity and task load among users for Google Scholar and JabRef related work user interface (User interface developed for Experiment). Subjective evaluation of user interface was done along with NASA-Task Load Index for workload measurement. Further sentiment analysis was conducted for validations of findings. Our study finds that serendipitous recommendations and user satisfaction is facilitated via transparency in recommender systems. Furthermore, we found that transparency enhances interactivity for users who are looking for novel and useful recommendations related to their work. This work contributes to human computer interaction studies of recommender systems and reviews the leading literature on transparency, serendipity, and recommender systems in learning environments. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink