@phdthesis{Voelske, author = {V{\"o}lske, Michael}, title = {Retrieval Enhancements for Task-Based Web Search}, doi = {10.25643/bauhaus-universitaet.3942}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20190709-39422}, school = {Bauhaus-Universit{\"a}t Weimar}, abstract = {The task-based view of web search implies that retrieval should take the user perspective into account. Going beyond merely retrieving the most relevant result set for the current query, the retrieval system should aim to surface results that are actually useful to the task that motivated the query. This dissertation explores how retrieval systems can better understand and support their users' tasks from three main angles: First, we study and quantify search engine user behavior during complex writing tasks, and how task success and behavior are associated in such settings. Second, we investigate search engine queries formulated as questions, and explore patterns in a large query log that may help search engines to better support this increasingly prevalent interaction pattern. Third, we propose a novel approach to reranking the search result lists produced by web search engines, taking into account retrieval axioms that formally specify properties of a good ranking.}, subject = {Information Retrieval}, language = {en} } @article{VoelskeGollubHagenetal., author = {V{\"o}lske, Michael and Gollub, Tim and Hagen, Matthias and Stein, Benno}, title = {A keyquery-based classification system for CORE}, series = {D-Lib Magazine}, journal = {D-Lib Magazine}, doi = {10.1045/november14-voelske}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20170426-31662}, abstract = {We apply keyquery-based taxonomy composition to compute a classification system for the CORE dataset, a shared crawl of about 850,000 scientific papers. Keyquery-based taxonomy composition can be understood as a two-phase hierarchical document clustering technique that utilizes search queries as cluster labels: In a first phase, the document collection is indexed by a reference search engine, and the documents are tagged with the search queries they are relevant—for their so-called keyqueries. In a second phase, a hierarchical clustering is formed from the keyqueries within an iterative process. We use the explicit topic model ESA as document retrieval model in order to index the CORE dataset in the reference search engine. Under the ESA retrieval model, documents are represented as vectors of similarities to Wikipedia articles; a methodology proven to be advantageous for text categorization tasks. Our paper presents the generated taxonomy and reports on quantitative properties such as document coverage and processing requirements.}, subject = {Massendaten}, language = {en} } @article{VakkariVoelskePotthastetal., author = {Vakkari, Pertti and V{\"o}lske, Michael and Potthast, Martin and Hagen, Matthias and Stein, Benno}, title = {Predicting essay quality from search and writing behavior}, series = {Journal of Association for Information Science and Technology}, volume = {2021}, journal = {Journal of Association for Information Science and Technology}, number = {volume 72, issue 7}, publisher = {Wiley}, address = {Hoboken, NJ}, doi = {10.1002/asi.24451}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20210804-44692}, pages = {839 -- 852}, abstract = {Few studies have investigated how search behavior affects complex writing tasks. We analyze a dataset of 150 long essays whose authors searched the ClueWeb09 corpus for source material, while all querying, clicking, and writing activity was meticulously recorded. We model the effect of search and writing behavior on essay quality using path analysis. Since the boil-down and build-up writing strategies identified in previous research have been found to affect search behavior, we model each writing strategy separately. Our analysis shows that the search process contributes significantly to essay quality through both direct and mediated effects, while the author's writing strategy moderates this relationship. Our models explain 25-35\% of the variation in essay quality through rather simple search and writing process characteristics alone, a fact that has implications on how search engines could personalize result pages for writing tasks. Authors' writing strategies and associated searching patterns differ, producing differences in essay quality. In a nutshell: essay quality improves if search and writing strategies harmonize—build-up writers benefit from focused, in-depth querying, while boil-down writers fare better with a broader and shallower querying strategy.}, subject = {Information Retrieval}, language = {en} }