@article{BakerWitte06, title = {{Mutation Mining---A Prospector's Tale}}, author = {Christopher J. O. Baker and Ren\'{e} Witte}, journal = {Information Systems Frontiers (ISF)}, month = {February}, number = 1, pages = {47--57}, volume = 8, year = 2006, description = {Mutation Mining - A Prospector's Tale | rene-witte.net}, biburl = {http://www.bibsonomy.org/bibtex/2931d9d3ebb1f6f27be9ce8a7af8afc61/renew}, keywords = {protein mutationminer text mining mutation} } @article{witte:3, title = {Text mining and software engineering: an integrated source code and document analysis approach}, author = {R. Witte and Q. Li and Y. Zhang and J. Rilling}, journal = {IET Software}, number = 1, pages = {3-16}, publisher = {IET}, volume = 2, year = 2008, url = {http://link.aip.org/link/?SEN/2/3/1}, doi = {10.1049/iet-sen:20070110}, abstract = {Documents written in natural languages constitute a major part of the artefacts produced during the software engineering life cycle. Especially during software maintenance or reverse engineering, semantic information conveyed in these documents can provide important knowledge for the software engineer. A text mining system capable of populating a software ontology with information detected in documents is presented. A particular novelty is the integration of results from automated source code analysis into a natural language processing pipeline, allowing to cross-link software artefacts represented in code and natural language on a semantic level.}, biburl = {http://www.bibsonomy.org/bibtex/2557915366a2587505d5c192da8e1b849/renew}, keywords = {software text engineering mining} } @inproceedings{keyhere, title = {Construction of Ontology-Based Software Repositories by Text Mining}, author = {Yan Wu and Harvey Siy and Mansour Zand and Victor Winter}, booktitle = { Computational Science – ICCS 2007 7th International Conference, Beijing, China, May 27 - 30, 2007, Proceedings, Part III }, pages = {790--797}, year = 2007, url = {http://dx.doi.org/10.1007/978-3-540-72588-6_128}, description = {SpringerLink - Book Chapter}, abstract = {Software document repositories store artifacts produced in the course of developing software products. But most repositories are simply archives of documents. It is not unusual to find projects where different software artifacts are scattered in unrelatedrepositories with varying levels of granularity and without a centralized management system. This makes the information availablein existing repositories difficult to reuse. In this paper, a methodology for constructing an ontology-based repository ofreusable knowledge is presented. The information in the repository is extracted from specification documents using text mining.Ontologies are used to guide the extraction process and organize the extracted information. The methodology is being usedto develop a repository of recurring and crosscutting aspects in software specification documents.}, biburl = {http://www.bibsonomy.org/bibtex/2a4549281d473c562152904f4e7393f43/renew}, keywords = {repository text software engineering ontology mining} } @article{1083153, title = {Text mining for software engineering: how analyst feedback impacts final results}, address = {New York, NY, USA}, author = {Jane Huffman Hayes and Alex Dekhtyar and Senthil Sundaram}, journal = {SIGSOFT Softw. Eng. Notes}, number = 4, pages = {1--5}, publisher = {ACM}, volume = 30, year = 2005, url = {http://portal.acm.org/citation.cfm?id=1082983.1083153}, issn = {0163-5948}, doi = {http://doi.acm.org/10.1145/1082983.1083153}, description = {Text mining for software engineering}, abstract = {The mining of textual artifacts is requisite for many important activities in software engineering: tracing of requirements; retrieval of components from a repository; location of manpage text for an area of question, etc. Many such activities leave the "final word" to the analyst --- have the relevant items been retrieved? are there other items that should have been retrieved? When analysts become a part of the text mining process, their decisions on the relevance of retrieved elements impact the final outcome of the activity. In this paper, we undertook a pilot study to examine the impact of analyst decisions on the final outcome of a task.}, biburl = {http://www.bibsonomy.org/bibtex/2dcbda00e6fadfafd0495274e1eeed893/renew}, keywords = {mining text engineering software} } @inproceedings{cbrw04, title = {{Enriching Protein Structure Visualizations with Mutation Annotations Obtained by Text Mining Protein Engineering Literature}}, address = {Markham, Ontario, Canada}, author = {Christopher J.O. Baker and Ren\'{e} Witte}, booktitle = {The 3rd Canadian Working Conference on Computational Biology (CCCB'04)}, month = {October 4}, note = {Co-located with IBM CASCON.}, year = 2004, url = {http://www.rene-witte.net/mutation-miner-cccb2004}, description = {Enriching Protein Structure Visualizations with Mutation Annotations Obtained by Text Mining Protein Engineering Literature | rene-witte.net}, biburl = {http://www.bibsonomy.org/bibtex/290d2de711cd825f63f6dd2b9aec4f7a5/renew}, keywords = {visualization protein text mining} } @article{WitteBaker07, title = {Towards A Systematic Evaluation of Protein Mutation Extraction Systems}, author = {Ren{\'{e}} Witte and Christopher J. O. Baker}, journal = {Journal of Bioinformatics and Computational Biology (JBCB)}, month = {December}, number = 6, pages = {1339--1359}, volume = 5, year = 2007, url = {http://rene-witte.net/evaluation-of-mutation-extraction-systems}, description = {Towards a Systematic Evaluation of Protein Mutation Extraction Systems | rene-witte.net}, biburl = {http://www.bibsonomy.org/bibtex/28d26f86d85973ba5346224cce574e59c/renew}, keywords = {mining text protein evaluation mutation} } @article{WKB_IJBRA2007, title = {Enhanced semantic access to the protein engineering literature using ontologies populated by text mining}, author = {Ren{\'{e}} Witte and Thomas Kappler and Christopher J. O. Baker}, journal = {Int.\ J.\ Bioinformatics Research and Applications (IJBRA)}, note = {PMID: 18048198}, number = 3, pages = {389--413}, volume = 3, year = 2007, url = {http://www.rene-witte.net/semantic-access-to-protein-engineering-literature}, description = {Enhanced Semantic Access to the Protein Engineering Literature using Ontologies Populated by Text Mining | rene-witte.net}, biburl = {http://www.bibsonomy.org/bibtex/2855d46b7fa0a5d08e86e068a5318e309/renew}, keywords = {text bioinformatics protein mining population engineering ontology} } @article{1224718, title = {Topic discovery based on text mining techniques}, address = {Tarrytown, NY, USA}, author = {Aurora Pons-Porrata and Rafael Berlanga-Llavori and Jos\'{e} Ruiz-Shulcloper}, journal = {Inf. Process. Manage.}, number = 3, pages = {752--768}, publisher = {Pergamon Press, Inc.}, volume = 43, year = 2007, url = {http://portal.acm.org/citation.cfm?id=1224718}, issn = {0306-4573}, doi = {http://dx.doi.org/10.1016/j.ipm.2006.06.001}, description = {Topic discovery based on text mining techniques}, abstract = {In this paper, we present a topic discovery system aimed to reveal the implicit knowledge present in news streams. This knowledge is expressed as a hierarchy of topic/subtopics, where each topic contains the set of documents that are related to it and a summary extracted from these documents. Summaries so built are useful to browse and select topics of interest from the generated hierarchies. Our proposal consists of a new incremental hierarchical clustering algorithm, which combines both partitional and agglomerative approaches, taking the main benefits from them. Finally, a new summarization method based on Testor Theory has been proposed to build the topic summaries. Experimental results in the TDT2 collection demonstrate its usefulness and effectiveness not only as a topic detection system, but also as a classification and summarization tool.}, biburl = {http://www.bibsonomy.org/bibtex/25095275ddb32f4138ee5018a6a4f3fc6/renew}, keywords = {topic mining detection text} } @article{keyhere, title = {A Method for Constructing a Movie-Selection Support System Based on Kansei Engineering}, author = {Noriaki Sato and Michiko Anse and Tsutomu Tabe}, journal = {Human Interface and the Management of Information. Methods, Techniques and Tools in Information Design}, pages = {526--534}, year = 2007, url = {http://dx.doi.org/10.1007/978-3-540-73345-4_60}, description = {SpringerLink - Book Chapter}, abstract = {When a person requests, for example, “I want to see a bright and exciting movie,” the words “bright” and “exciting” are called Kansei keywords. With a retrieval system to retrieve recommended movies using these Kansei keywords, a viewer will be able to select movies that fit the Kansei without actually having to view samples or previews of the movies. The purpose of this research is to clarify a method toconstruct a support system capable of selecting movies that fit the viewer’s Kansei, and to verify the effectiveness of this method based on Kansei engineering, for the selection of recommended movies. To accomplish this, we extract the features of a movie using factorfactoranalysis from data from a Semantic Differential Gauge questionnaire, then link the viewer’s Kansei with the features using multiple linear regression analysis. After constructing a prototype � system to verify the effectiveness,ten examinees viewed a movie selected by the prototype � system. “The selected movie fit the Kansei” at a level of about 70percent.}, biburl = {http://www.bibsonomy.org/bibtex/2aa760f47d7e925c6e66d6fa720b3dfe7/renew}, keywords = {mining movie opinion review} } @inproceedings{1183625, title = {Movie review mining and summarization}, address = {New York, NY, USA}, author = {Li Zhuang and Feng Jing and Xiao-Yan Zhu}, booktitle = {CIKM '06: Proceedings of the 15th ACM international conference on Information and knowledge management}, pages = {43--50}, publisher = {ACM}, year = 2006, url = {http://portal.acm.org/citation.cfm?id=1183614.1183625}, location = {Arlington, Virginia, USA}, isbn = {1-59593-433-2}, doi = {http://doi.acm.org/10.1145/1183614.1183625}, description = {Movie review mining and summarization}, abstract = {With the flourish of the Web, online review is becoming a more and more useful and important information resource for people. As a result, automatic review mining and summarization has become a hot research topic recently. Different from traditional text summarization, review mining and summarization aims at extracting the features on which the reviewers express their opinions and determining whether the opinions are positive or negative. In this paper, we focus on a specific domain - movie review. A multi-knowledge based approach is proposed, which integrates WordNet, statistical analysis and movie knowledge. The experimental results show the effectiveness of the proposed approach in movie review mining and summarization.}, biburl = {http://www.bibsonomy.org/bibtex/2fda331d7f37683a6b4a06fd1b6f7c3da/renew}, keywords = {movie summarization opinion mining review} } @book{keyhere, title = {Web Data Mining}, author = {Bing Liu}, note = {http://www.cs.uic.edu/~liub/WebMiningBook.html}, year = 2007, url = {http://dx.doi.org/10.1007/978-3-540-37882-2}, description = {SpringerLink - Book}, biburl = {http://www.bibsonomy.org/bibtex/2c88cd82a9957beba3aa8616d93caee94/renew}, keywords = {data web mining} } @article{keyhere, title = {Opinion Mining}, journal = {Web Data Mining}, pages = {411--447}, year = 2007, url = {http://dx.doi.org/10.1007/978-3-540-37882-2_11}, description = {SpringerLink - Book Chapter}, biburl = {http://www.bibsonomy.org/bibtex/2c5803a7c46e486e991787011d952608f/renew}, keywords = {mining opinion} }