One for all, and all for one? Identifying clusters of user behaviour in intranet search engine log files

Övrigt konferensbidrag, 2007

In recent years a substantial amount of research has been focusing on how ordinary web users interact with search engines. However, these users are tacitly assumed to be a homogeneous group by researcher and vendor alike. We argue that search engine users should not be treated collectively and by applying automatic clustering technique based on self-organising maps to search engine log files from a corporate intranet, we show that users can be separated into distinguishable segments based on their search behaviour. Analysis of these segments teaches us more about (intranet) searching and when designing and implementing future tools for information seeking and retrieval, these tools can be targeted to specific segments rather than to the population as a whole. We found that a large group of users appear to be casual “fact seekers” who would benefit from higher precision, a smaller group of users were more holistically oriented and would likely benefit from higher recall, whereas a third clique of users seemed to constitute the information-seeking savvy employees. All these three groups may raise different design implications for search tool developers.