@phdthesis{Potthast, author = {Potthast, Martin}, title = {Technologies for Reusing Text from the Web}, doi = {10.25643/bauhaus-universitaet.1566}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20120217-15663}, school = {Bauhaus-Universit{\"a}t Weimar}, pages = {237}, abstract = {Texts from the web can be reused individually or in large quantities. The former is called text reuse and the latter language reuse. We first present a comprehensive overview of the different ways in which text and language is reused today, and how exactly information retrieval technologies can be applied in this respect. The remainder of the thesis then deals with specific retrieval tasks. In general, our contributions consist of models and algorithms, their evaluation, and for that purpose, large-scale corpus construction. The thesis divides into two parts. The first part introduces technologies for text reuse detection, and our contributions are as follows: (1) A unified view of projecting-based and embedding-based fingerprinting for near-duplicate detection and the first time evaluation of fingerprint algorithms on Wikipedia revision histories as a new, large-scale corpus of near-duplicates. (2) A new retrieval model for the quantification of cross-language text similarity, which gets by without parallel corpora. We have evaluated the model in comparison to other models on many different pairs of languages. (3) An evaluation framework for text reuse and particularly plagiarism detectors, which consists of tailored detection performance measures and a large-scale corpus of automatically generated and manually written plagiarism cases. The latter have been obtained via crowdsourcing. This framework has been successfully applied to evaluate many different state-of-the-art plagiarism detection approaches within three international evaluation competitions. The second part introduces technologies that solve three retrieval tasks based on language reuse, and our contributions are as follows: (4) A new model for the comparison of textual and non-textual web items across media, which exploits web comments as a source of information about the topic of an item. In this connection, we identify web comments as a largely neglected information source and introduce the rationale of comment retrieval. (5) Two new algorithms for query segmentation, which exploit web n-grams and Wikipedia as a means of discerning the user intent of a keyword query. Moreover, we crowdsource a new corpus for the evaluation of query segmentation which surpasses existing corpora by two orders of magnitude. (6) A new writing assistance tool called Netspeak, which is a search engine for commonly used language. Netspeak indexes the web in the form of web n-grams as a source of writing examples and implements a wildcard query processor on top of it.}, subject = {Information Retrieval}, language = {en} } @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{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 harmonizeā€”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} }