방법 비교

	Search Session Analysis	Relevance Feedback Evaluation
분야	Library Information Science	Library Information Science
계열	Process / pipeline	Process / pipeline
기원 연도	2000	1990
창시자	Bernard J. Jansen, Amanda Spink & Tefko Saracevic; web-search session research	Gerard Salton & Chris Buckley (building on J. J. Rocchio)
유형	Analysis pipeline for multi-query search episodes	Evaluation pipeline for relevance-feedback query reformulation
원전	Jansen, B. J., Spink, A., & Saracevic, T. (2000). Real life, real users, and real needs: a study and analysis of user queries on the web. Information Processing & Management, 36(2), 207-227.	Salton, G., & Buckley, C. (1990). Improving retrieval performance by relevance feedback. Journal of the American Society for Information Science, 41(4), 288-297.
별칭	Session Analysis, Search Episode Analysis, Multi-Query Session Analysis, Session-Based Search Evaluation	Rocchio Feedback Evaluation, Feedback Effectiveness Measurement, Residual Collection Evaluation, Relevance Feedback Assessment
관련	3	3
요약	Search session analysis studies the whole search episode — the sequence of queries, reformulations, clicks, and pauses a user produces while pursuing a single information need — rather than scoring one query in isolation. Real searching is rarely one shot: users issue a query, scan results, refine their wording, follow links, and try again until they succeed or give up. Building on the transaction-log tradition of Jansen, Spink, and Saracevic and the large-scale web studies of Silverstein and colleagues, session analysis reconstructs these episodes from logs, classifies how queries evolve, measures the effort expended, models the transitions between actions, and assesses whether and how the session succeeded. It is the bridge between single-query laboratory evaluation and the messy, iterative reality of how people actually find information.	Relevance feedback evaluation measures how much a retrieval system improves when it reformulates a query using user judgments on the first results. The technique that defined the field is Rocchio's vector-space feedback, in which documents the user marks relevant pull the query vector toward themselves and documents marked non-relevant push it away; Salton and Buckley's 1990 study systematized its evaluation and showed substantial effectiveness gains. The central methodological challenge is fairness: because the user has already seen and judged some documents, naively re-scoring the whole collection rewards the system for re-finding documents it was just told about. Residual-collection and frozen-rank evaluation solve this by measuring improvement only on documents the user has not yet seen.