These proceedings contain the refereed papers and posters presented at the S- ond International Conference on the Theory of Information Retrieval (ICTIR 2009), held at Microsoft Research in Cambridge, UK, September 10-11, 2009. This biennial international conference provides an opportunity for the p- sentation of the latest work describing theoretical advances in the ?eld of inf- mation retrieval (IR). The ?rst ICTIR was held in Budapest in October 2007, organizedby Keith van Rijsbergen, Sa ´ndor Dominich, S´ andor Daran ´ yi,and F- enc Kiss. ICTIR was brought about by the growing interest in the consecutive workshops run at ACM SIGIR each year from 2000 until 2005 on Mathematical and Formal Methods in IR (Athens, Greece, 2000; New Orleans, USA, 2001; Tampere, Finland, 2002; Toronto, Canada, 2003; She?eld, UK, 2004; Salvador, Brazil, 2005). This sustained initiative was in a large part down to the det- mination of San ´ dor Dominich and his passion for all things good, formal and mathematical. The foundation and the success of ICTIR is a direct result of his commitment and dedication to fostering research and development into the theoretical underpinnings of IR. His dedication is epitomized by his two books on the subject: Mathematical Foundations in Information Retrieval published in 2001, and The Modern Algebra of Information Retrieval published in 2008.
This book constitutes the refereed proceedings of the Second International Conference on the Theory of Information Retrieval, ICTIR 2009, held in Cambridge, UK, in September 2009.
The 18 revised full papers, 14 short papers, and 11 posters presented together with one invited talk were carefully reviewed and selected from 82 submissions. The papers are categorized into four main themes: novel IR models, evaluation, efficiency, and new perspectives in IR. Twenty-one papers fall into the general theme of novel IR models, ranging from various retrieval models, query and term selection models, Web IR models, developments in novelty and diversity, to the modeling of user aspects. There are four papers on new evaluation methodologies, e.g., modeling score distributions, evaluation over sessions, and an axiomatic framework for XML retrieval evaluation. Three papers focus on the issue of efficiency and offer solutions to improve the tractability of PageRank, data cleansing practices for training classifiers, and approximate search for distributed IR. Finally, four papers look into new perspectives of IR and shed light on some new emerging areas of interest, such as the application and adoption of quantum theory in IR.