@inproceedings{Grube.2017, abstract = {Patients use various sources to obtain information on pharmaceutical drugs. Mobile health care applications (apps) providing drug information to users are increasingly made available and of rising importance for the health care domain. However, apps usually offer functionality that only medical professionals or vendors consider useful for patients, although their considerations are not likely to meet patient expectations. In our exploratory study, we identify 33 features patients expect in apps for drug information provision with interviews and empirically assess their perceived importance in an online survey. Results indicate that patients desire personalization features for provided information but not for the app interface. This work contributes to research and practice by identifying and empirically ranking drug information provision features patients find important. We furthermore establish a foundation for future research on effective mobile drug information provision and provide insights for practice on development of patient-centered mobile health apps.}, address = {Honolulu, HI, USA}, author = {Grube, Anton and Dehling, Tobias and Sunyaev, Ali}, booktitle = {Proceedings 50th Hawaii International Conference on System Sciences}, interhash = {65de8e95ddc4cb6b2471d77273730f77}, intrahash = {88b37b035e4febd631640dd412e57d73}, month = {January}, pages = {3577-3586}, title = {How Do Patients Expect Apps to Provide Drug Information?}, url = {http://scholarspace.manoa.hawaii.edu/bitstream/10125/41591/1/paper0442.pdf}, urldate = {23.01.2017}, year = 2017 } @proceedings{thierrypoibeau2013multisource, abstract = {Information extraction (IE) and text summarization (TS) are powerful technologies for finding relevant pieces of information in text and presenting them to the user in condensed form. The ongoing information explosion makes IE and TS critical for successful functioning within the information society. These technologies face particular challenges due to the inherent multi-source nature of the information explosion. The technologies must now handle not isolated texts or individual narratives, but rather large-scale repositories and streams--in general, in multiple languages--containing a multiplicity of perspectives, opinions, or commentaries on particular topics, entities or events. There is thus a need to adapt existing techniques and develop new ones to deal with these challenges. This volume contains a selection of papers that present a variety of methodologies for content identification and extraction, as well as for content fusion and regeneration. The chapters cover various aspects of the challenges, depending on the nature of the information sought--names vs. events,-- and the nature of the sources--news streams vs. image captions vs. scientific research papers, etc. This volume aims to offer a broad and representative sample of studies from this very active research field.}, address = {Berlin; New York}, editor = {Poibeau, Thierry and Saggion, Horacio and Piskorski, Jakub and Yangarber, Roman}, interhash = {b1d51398d5660ed1e16f40d74cc815db}, intrahash = {21816f2809a2b58397acce5ac9558d28}, isbn = {9783642285691 3642285694 3642285686 9783642285684}, publisher = {Springer}, refid = {808368416}, title = {Multi-source, multilingual information extraction and summarization}, url = {http://link.springer.com/book/10.1007/978-3-642-28569-1}, year = 2013 } @incollection{piskorski2013information, abstract = {In this chapter we present a brief overview of Information Extraction, which is an area of natural language processing that deals with finding factual information in free text. In formal terms, }, author = {Piskorski, Jakub and Yangarber, Roman}, booktitle = {Multi-source, Multilingual Information Extraction and Summarization}, doi = {10.1007/978-3-642-28569-1_2}, editor = {Poibeau, Thierry and Saggion, Horacio and Piskorski, Jakub and Yangarber, Roman}, interhash = {276145faeb3b45461f09f6ae5aabef5e}, intrahash = {55c1de993e15515d35b68a512088d607}, isbn = {978-3-642-28568-4}, language = {English}, pages = {23-49}, publisher = {Springer Berlin Heidelberg}, series = {Theory and Applications of Natural Language Processing}, title = {Information Extraction: Past, Present and Future}, url = {http://dx.doi.org/10.1007/978-3-642-28569-1_2}, year = 2013 } @book{manning2008, author = {Manning, Christopher D. and Raghavan, Prabhakar and Schütze, Hinrich}, interhash = {2e574e46b7668a7268e7f02b46f4d9bb}, intrahash = {9f4ab13e07b48b9723113aa74224be65}, publisher = {Cambridge University Press}, title = {Introduction to Information Retrieval}, year = 2008 } @inproceedings{heckner2009personal, address = {San Jose, CA, USA}, author = {Heckner, Markus and Heilemann, Michael and Wolff, Christian}, booktitle = {Int'l AAAI Conference on Weblogs and Social Media (ICWSM)}, interhash = {f954e699dc6ca2d0abbe5f6ebe166dc7}, intrahash = {d1074484ea350ad88400fe4fc6984874}, month = may, title = {Personal Information Management vs. Resource Sharing: Towards a Model of Information Behaviour in Social Tagging Systems}, year = 2009 } @inproceedings{jaschke2013attribute, abstract = {We propose an approach for supporting attribute exploration by web information retrieval, in particular by posing appropriate queries to search engines, crowd sourcing systems, and the linked open data cloud. We discuss underlying general assumptions for this to work and the degree to which these can be taken for granted.}, author = {Jäschke, Robert and Rudolph, Sebastian}, booktitle = {Contributions to the 11th International Conference on Formal Concept Analysis}, editor = {Cellier, Peggy and Distel, Felix and Ganter, Bernhard}, interhash = {000ab7b0ae3ecd1d7d6ceb39de5c11d4}, intrahash = {45e900e280661d775d8da949baee3747}, month = may, organization = {Technische Universität Dresden}, pages = {19--34}, title = {Attribute Exploration on the Web}, url = {http://nbn-resolving.de/urn:nbn:de:bsz:14-qucosa-113133}, urn = {urn:nbn:de:bsz:14-qucosa-113133}, year = 2013 } @inproceedings{chrupala2010named, author = {Chrupala, Grzegorz and Klakow, Dietrich}, booktitle = {LREC}, crossref = {conf/lrec/2010}, editor = {Calzolari, Nicoletta and Choukri, Khalid and Maegaard, Bente and Mariani, Joseph and Odijk, Jan and Piperidis, Stelios and Rosner, Mike and Tapias, Daniel}, ee = {http://www.lrec-conf.org/proceedings/lrec2010/summaries/538.html}, interhash = {85b8f5e04b66df3fe9411fc8f81ae43a}, intrahash = {68b98f37dc2dd0a89f580d9e6b65c780}, isbn = {2-9517408-6-7}, publisher = {European Language Resources Association}, title = {A Named Entity Labeler for German: Exploiting Wikipedia and Distributional Clusters.}, url = {http://lexitron.nectec.or.th/public/LREC-2010_Malta/pdf/538_Paper.pdf}, year = 2010 } @techreport{ritchie2009citation, abstract = {This thesis investigates taking words from around citations to scientific papers in order to create an enhanced document representation for improved information retrieval. This method parallels how anchor text is commonly used in Web retrieval. In previous work, words from citing documents have been used as an alternative representation of the cited document but no previous experiment has combined them with a full-text document representation and measured effectiveness in a large scale evaluation. The contributions of this thesis are twofold: firstly, we present a novel document representation, along with experiments to measure its effect on retrieval effectiveness, and, secondly, we document the construction of a new, realistic test collection of scientific research papers, with references (in the bibliography) and their associated citations (in the running text of the paper) automatically annotated. Our experiments show that the citation-enhanced document representation increases retrieval effectiveness across a range of standard retrieval models and evaluation measures. In Chapter 2, we give the background to our work, discussing the various areas from which we draw together ideas: information retrieval, particularly link structure analysis and anchor text indexing, and bibliometrics, in particular citation analysis. We show that there is a close relatedness of ideas between these areas but that these ideas have not been fully explored experimentally. Chapter 3 discusses the test collection paradigm for evaluation of information retrieval systems and describes how and why we built our test collection. In Chapter 4, we introduce the ACL Anthology, the archive of computational linguistics papers that our test collection is centred around. The archive contains the most prominent publications since the beginning of the field in the early 1960s, consisting of one journal plus conferences and workshops, resulting in over 10,000 papers. Chapter 5 describes how the PDF papers are prepared for our experiments, including identification of references and citations in the papers, once converted to plain text, and extraction of citation information to an XML database. Chapter 6 presents our experiments: we show that adding citation terms to the full-text of the papers improves retrieval effectiveness by up to 7.4%, that weighting citation terms higher relative to paper terms increases the improvement and that varying the context from which citation terms are taken has a significant effect on retrieval effectiveness. Our main hypothesis that citation terms enhance a full-text representation of scientific papers is thus proven. There are some limitations to these experiments. The relevance judgements in our test collection are incomplete but we have experimentally verified that the test collection is, nevertheless, a useful evaluation tool. Using the Lemur toolkit constrained the method that we used to weight citation terms; we would like to experiment with a more realistic implementation of term weighting. Our experiments with different citation contexts did not conclude an optimal citation context; we would like to extend the scope of our investigation. Now that our test collection exists, we can address these issues in our experiments and leave the door open for more extensive experimentation. }, address = {Cambridge, UK}, author = {Ritchie, Anna}, institution = {University of Cambridge}, interhash = {f086fdcd7eb1df44ef67b96f2e91996c}, intrahash = {aa4271a2a958fe2c1a65dbdd508d8de7}, issn = {1476-2986}, month = mar, number = 744, title = {Citation context analysis for information retrieval}, url = {https://www.cl.cam.ac.uk/techreports/UCAM-CL-TR-744.pdf}, year = 2009 } @article{shannon1951prediction, author = {Shannon, Claude Elwood}, interhash = {daabc21c7f6e71f6e78a10c8d3492927}, intrahash = {2e79cf0f6022645a632b13e081b0b035}, journal = {Bell System Technical Journal}, month = jan, pages = {50--64}, title = {Prediction and Entropy of Printed English}, url = {http://languagelog.ldc.upenn.edu/myl/Shannon1950.pdf}, volume = 30, year = 1951 } @article{shannon1948mathematical, author = {Shannon, Claude E.}, interhash = {754130207906fcec16a53d330eeff348}, intrahash = {b6bc42c140f0147cd6a1781d75fcb897}, journal = {The Bell System Technical Journal}, month = {July, October}, pages = {379--423, 623--656}, title = {A Mathematical Theory of Communication}, url = {http://cm.bell-labs.com/cm/ms/what/shannonday/shannon1948.pdf}, volume = 27, year = 1948 }