Adaptive information agents in distributed textual environments
AGENTS '98 Proceedings of the second international conference on Autonomous agents
Learning users' interests by unobtrusively observing their normal behavior
Proceedings of the 5th international conference on Intelligent user interfaces
Stuff I've seen: a system for personal information retrieval and re-use
Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval
Improving personalized web search using result diversification
SIGIR '06 Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval
Interest-based personalized search
ACM Transactions on Information Systems (TOIS)
A New Framework for Theory-Based Interaction Design Applied to Serendipitous Information Retrieval
ACM Transactions on Computer-Human Interaction (TOCHI)
To personalize or not to personalize: modeling queries with variation in user intent
Proceedings of the 31st annual international ACM SIGIR conference on Research and development in information retrieval
Hi-index | 0.01 |
Personalization is viewed as a potential solution to the "information overload" problem. In contrast, serendipity is a natural part of human information seeking process that can lead to unexpected and useful discoveries. It appears both serendipity and personalization are important. However, it remains unclear how these modes of interaction impact content retrieval and consumption. To empirically analyze the influence of personalization and serendipity on information retrieval, a medical news information system named MedSIFTER was developed. The system can personalize the presentation of news articles based on users' interest profiles. Using a control variable, built into the system, MeSIFTER's personalization level can be modulated, ranging from high to low (or zero). In this study, based on MedlinePlus as main information source, three different system modalities were compared (zero, low, and high levels of personalization). The experimental analysis engaged three different user groups, over a four week period. Strong evidence of serendipity was found across all three user groups, independent of the level of personalization. Users also appeared to be uniformly satisfied regardless of the level of personalization.