{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,5]],"date-time":"2025-10-05T19:47:20Z","timestamp":1759693640321},"publisher-location":"Berlin, Heidelberg","reference-count":49,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642352355"},{"type":"electronic","value":"9783642352362"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-35236-2_62","type":"book-chapter","created":{"date-parts":[[2012,11,20]],"date-time":"2012-11-20T01:36:35Z","timestamp":1353375395000},"page":"618-629","source":"Crossref","is-referenced-by-count":17,"title":["On Text Preprocessing for Opinion Mining Outside of Laboratory Environments"],"prefix":"10.1007","author":[{"given":"Gerald","family":"Petz","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Micha\u0142","family":"Karpowicz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Harald","family":"F\u00fcrschu\u00df","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Auinger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Stephan M.","family":"Winkler","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Susanne","family":"Schaller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andreas","family":"Holzinger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"62_CR1","doi-asserted-by":"publisher","DOI":"10.3139\/9783446415805","volume-title":"Web 2.0. Konzepte, Anwendungen, Technologien","author":"T. Alby","year":"2008","unstructured":"Alby, T.: Web 2.0. Konzepte, Anwendungen, Technologien, 3rd edn. Hanser, M\u00fcnchen (2008)","edition":"3"},{"key":"62_CR2","doi-asserted-by":"crossref","unstructured":"Nelles, O.: Nonlinear system identification: from classical approaches to neural networks and fuzzy models. Springer (2001)","DOI":"10.1007\/978-3-662-04323-3_17"},{"key":"62_CR3","series-title":"Data-centric systems and applications","volume-title":"Web data mining. Exploring hyperlinks, contents, and usage data","author":"B. Liu","year":"2008","unstructured":"Liu, B.: Web data mining. Exploring hyperlinks, contents, and usage data, 2nd edn. Data-centric systems and applications. Springer, Berlin (2008)","edition":"2"},{"issue":"271","key":"62_CR4","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1007\/BF03340441","volume":"47","author":"U. Steinecke","year":"2010","unstructured":"Steinecke, U., Straub, W.: Unstrukturierte Daten im Business Intelligence. Vorgehen, Ergebnisse und Erfahrungen in der praktischen Umsetzung. HMD - Praxis der Wirtschaftsinformatik\u00a047(271), 91\u2013101 (2010)","journal-title":"Vorgehen, Ergebnisse und Erfahrungen in der praktischen Umsetzung. HMD - Praxis der Wirtschaftsinformatik"},{"key":"62_CR5","doi-asserted-by":"crossref","unstructured":"Guozheng, Z., Faming, Z., Fang, W., Jian, L.: Knowledge Creation in Marketing Based on Data Mining. In: International Conference on Intelligent Computation Technology and Automation (ICICTA), vol.\u00a01, pp. 782\u2013786 (2008)","DOI":"10.1109\/ICICTA.2008.45"},{"key":"62_CR6","unstructured":"Holzinger, A.: Weakly Structured Data in Health-Informatics. In: Proceedings of INTERACT 2011 International Conference on Human-Computer Interaction, Workshop: Promoting and Supporting Healthy Living by Design, pp. 5\u20137 (2011)"},{"key":"62_CR7","unstructured":"Holzinger, A.: On Knowledge Discovery and Interactive Intelligent Visualization of Biomedical Data. In: Proceedings of the 9th International Joint Conference on e-Business and Telecommunications (ICETE 2012), pp. IS9\u2013IS20 (2012)"},{"issue":"22","key":"62_CR8","first-page":"3781","volume":"14","author":"A. Holzinger","year":"2008","unstructured":"Holzinger, A., Geierhofer, R., Modritscher, F., Tatzl, R.: Semantic Information in Medical Information Systems: Utilization of Text Mining Techniques to Analyze Medical Diagnoses. Journal of Universal Computer Science\u00a014(22), 3781\u20133795 (2008)","journal-title":"Journal of Universal Computer Science"},{"key":"62_CR9","unstructured":"Maynard, D., Bontcheva, K., Rout, D.: Challenges in developing opinion mining tools for social media. In: Proceedings of @NLP\u00a0can u tag #user_generated_content?! Workshop at LREC 2012, Istanbul, Turkey (May 2012)"},{"issue":"3","key":"62_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1361684.1361685","volume":"26","author":"A. Abbasi","year":"2008","unstructured":"Abbasi, A., Chen, H., Salem, A.: Sentiment analysis in multiple languages: Feature selection for opinion classification in Web forums. ACM Trans. Inf. Syst.\u00a026(3), 12:1\u201312:34 (2008)","journal-title":"ACM Trans. Inf. Syst."},{"key":"62_CR11","first-page":"43","volume-title":"Proceedings of the 18th International Joint Conference on Artificial Intelligence","author":"L. Yi","year":"2003","unstructured":"Yi, L., Liu, B.: Web page cleaning for web mining through feature weighting. In: Proceedings of the 18th International Joint Conference on Artificial Intelligence, pp. 43\u201348. Morgan Kaufmann Publishers Inc., San Francisco (2003)"},{"key":"62_CR12","doi-asserted-by":"crossref","unstructured":"Gamon, M.: Sentiment classification on customer feedback data: noisy data, large feature vectors, and the role of linguistic analysis. In: Proceedings of the 20th International Conference on Computational Linguistics (2004)","DOI":"10.3115\/1220355.1220476"},{"issue":"268","key":"62_CR13","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1007\/BF03340384","volume":"46","author":"C. Kaiser","year":"2009","unstructured":"Kaiser, C.: Opinion Mining im Web 2.0 \u2013 Konzept und Fallbeispiel. HMD - Praxis der Wirtschaftsinformatik\u00a046(268), 90\u201399 (2009)","journal-title":"HMD - Praxis der Wirtschaftsinformatik"},{"key":"62_CR14","doi-asserted-by":"crossref","unstructured":"Kim, S.-M., Hovy, E.: Determining the Sentiment of Opinions. In: Proceedings of 20th International Conference on Computational Linguistics, Geneva, Switzerland, pp. 1367\u20131373 (2004)","DOI":"10.3115\/1220355.1220555"},{"key":"62_CR15","doi-asserted-by":"crossref","unstructured":"Nadali, S., Masrah, A.A.M., Rabiah, A.K.: Sentiment Classification of Customer Reviews Based on Fuzzy logic. In: Mahmood, A.K. (ed.) International Symposium in Information Technology (ITSim), pp. 1037\u20131044. IEEE (2010)","DOI":"10.1109\/ITSIM.2010.5561583"},{"key":"62_CR16","doi-asserted-by":"crossref","unstructured":"Hu, M., Liu, B.: Mining and summarizing customer reviews. In: Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 168\u2013177 (2004)","DOI":"10.1145\/1014052.1014073"},{"key":"62_CR17","unstructured":"Jindal, N., Liu, B.: Mining comparative sentences and relations. In: Proceedings of the 21st National Conference on Artificial Intelligence, vol. 2, pp. 1331\u20131336. AAAI Press (2006)"},{"key":"62_CR18","doi-asserted-by":"crossref","unstructured":"Hatzivassiloglou, V., Wiebe, J.: Effects of Adjective Orientation and Gradability on Sentence Subjectivity. In: Proceedings of the 18th Conference on Computational Linguistics, pp. 299\u2013305 (2000)","DOI":"10.3115\/990820.990864"},{"key":"62_CR19","doi-asserted-by":"crossref","unstructured":"Turney, P.D.: Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, Philadelphia, PA, USA, pp. 417\u2013424 (2002)","DOI":"10.3115\/1073083.1073153"},{"key":"62_CR20","doi-asserted-by":"crossref","unstructured":"Wiebe, J., Mihalcea, R.: Word Sense and Subjectivity. In: Proceedings of the 21st International Conference on Computational Linguistics and the 44th Annual Meeting of the Association for Computational Linguistics, pp. 1065\u20131072 (2006)","DOI":"10.3115\/1220175.1220309"},{"key":"62_CR21","volume-title":"International Conference on Web Search & Data Mining","author":"X. Ding","year":"2008","unstructured":"Ding, X., Liu, B., Yu, P.S.: A Holistic Lexicon-Based Approach to Opinion Mining. In: International Conference on Web Search & Data Mining, Palo Alto, California, February 11-12. ACM, New York (2008)"},{"key":"62_CR22","doi-asserted-by":"crossref","unstructured":"Popescu, A.-M., Etzioni, O.: Extracting Product Features and Opinions from Reviews. In: Proceedings of Human Language Technology Conference, pp. 339\u2013346 (2005)","DOI":"10.3115\/1220575.1220618"},{"key":"62_CR23","first-page":"45","volume":"2","author":"S. Tong","year":"2001","unstructured":"Tong, S., Koller, D.: Support Vector Machine Active Learning with Applications to Text Classification. Journal of Machine Learning Research\u00a02, 45\u201366 (2001)","journal-title":"Journal of Machine Learning Research"},{"key":"62_CR24","doi-asserted-by":"crossref","unstructured":"Weisberg, S.: Applied linear regression, vol.\u00a0528. Wiley (2005)","DOI":"10.1002\/0471704091"},{"key":"62_CR25","doi-asserted-by":"crossref","unstructured":"Vapnik, V.: The nature of statistical learning theory. Springer (2000)","DOI":"10.1007\/978-1-4757-3264-1"},{"key":"62_CR26","unstructured":"Witten, I., Frank, E.: Data Mining: Practical machine learning tools and techniques. Morgan Kaufmann (2005)"},{"issue":"7","key":"62_CR27","first-page":"1109","volume":"17","author":"M. Kreuzthaler","year":"2011","unstructured":"Kreuzthaler, M., Bloice, M.D., Faulstich, L., Simonic, K.M., Holzinger, A.: A Comparison of Different Retrieval Strategies Working on Medical Free Texts. Journal of Universal Computer Science\u00a017(7), 1109\u20131133 (2011)","journal-title":"Journal of Universal Computer Science"},{"key":"62_CR28","doi-asserted-by":"crossref","unstructured":"Holzinger, A., Simonic, K.M., Yildirim, P.: Disease-disease relationships for rheumatic diseases Web-based biomedical textmining and knowledge discovery to assist medical decision making. In: IEEE COMPSAC, pp. 573\u2013580 (2012)","DOI":"10.1109\/COMPSAC.2012.77"},{"key":"62_CR29","unstructured":"Koza, J.: Genetic programming II: automatic discovery of reusable programs (1994)"},{"key":"62_CR30","doi-asserted-by":"crossref","unstructured":"Affenzeller, M., Wagner, S., Winkler, S.: Genetic Algorithms and Genetic Programming: Modern Concepts and Practical Applications. Numerical Insights. Taylor & Francis (2009)","DOI":"10.1201\/9781420011326"},{"issue":"4","key":"62_CR31","doi-asserted-by":"publisher","first-page":"732","DOI":"10.1016\/j.dss.2010.08.024","volume":"50","author":"X. Bai","year":"2011","unstructured":"Bai, X.: Predicting consumer sentiments from online text. Decision Support Systems\u00a050(4), 732\u2013742 (2011)","journal-title":"Decision Support Systems"},{"key":"62_CR32","doi-asserted-by":"publisher","first-page":"375","DOI":"10.1145\/1645953.1646003","volume-title":"Proceedings of the 18th ACM Conference on Information and Knowledge Management","author":"C. Lin","year":"2009","unstructured":"Lin, C., He, Y.: Joint sentiment\/topic model for sentiment analysis. In: Proceedings of the 18th ACM Conference on Information and Knowledge Management, pp. 375\u2013384. ACM, New York (2009)"},{"key":"62_CR33","unstructured":"Faschang, P., Petz, G., Dorfer, V., Kern, T., Winkler, S.M.: An Approach to Mining Consumer\u2019s Opinion on the Web. In: 13th International Conference on Computer Aided Systems Theory, Eurocast 2011, pp. 37\u201339 (2011)"},{"key":"62_CR34","unstructured":"Faschang, P., Petz, G., Wimmer, M., Dorfer, V., Winkler, S.M.: Evaluation of Tools for Opinion Mining. In: EEE (ed.) Proceedings of the 2011 International Conference on E-Learning, E-Business, Enterprise Information Systems & E-Government, Las Vegas, pp. 3\u20139 (2011)"},{"key":"62_CR35","unstructured":"Schaller, S., Winkler, S.M., Dorfer, V., Petz, G., F\u00fcrschu\u00df, H.: A Machine Learning Suite for Opinion Mining in Web. In: Proceedings of the 14th International Asia Pacific Conference on Computer Aided System Theory, IEEE APCast (2012)"},{"key":"62_CR36","unstructured":"Mihalcea, R., Banea, C., Wiebe, J.: Learning Multilingual Subjective Language via Cross-Lingual Projections. In: Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics, pp. 976\u2013983 (2007)"},{"issue":"4","key":"62_CR37","doi-asserted-by":"publisher","first-page":"48702","DOI":"10.1103\/PhysRevLett.88.048702","volume":"88","author":"D. Benedetto","year":"2002","unstructured":"Benedetto, D., Caglioti, E., Loreto, V.: Language Trees and Zipping. Phys. Rev. Lett.\u00a088(4), 48702 (2002), doi:10.1103\/PhysRevLett.88.048702","journal-title":"Phys. Rev. Lett."},{"key":"62_CR38","unstructured":"Grefenstette, G.: Comparing two language identification schemes. In: Proceedings of the 3rd International Conference on Statistical Analysis of Textual Data (JADT 1995), pp. 263\u2013268 (1995)"},{"key":"62_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1007\/978-3-642-00382-0_29","volume-title":"Computational Linguistics and Intelligent Text Processing","author":"R. \u0158eh\u016f\u0159ek","year":"2009","unstructured":"\u0158eh\u016f\u0159ek, R., Kolkus, M.: Language Identification on the Web: Extending the Dictionary Method. In: Gelbukh, A. (ed.) CICLing 2009. LNCS, vol.\u00a05449, pp. 357\u2013368. Springer, Heidelberg (2009)"},{"key":"62_CR40","unstructured":"Cavnar, W.B., Trenkle, J.M.: Trenkle: N-Gram-Based Text Categorization. In: Proceedings of SDAIR 1994, 3rd Annual Symposium on Document Analysis and Information Retrieval, pp. 161\u2013175 (1994)"},{"key":"62_CR41","unstructured":"Dunning, T.: Statistical Identification of Language (1994)"},{"issue":"2","key":"62_CR42","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/565117.565137","volume":"31","author":"A.H.F. Laender","year":"2002","unstructured":"Laender, A.H.F., Ribeiro-Neto, B.A., da Silva, A.S., Teixeira, J.S.: A brief survey of web data extraction tools. SIGMOD Rec.\u00a031(2), 84\u201393 (2002), doi:10.1145\/565117.565137","journal-title":"SIGMOD Rec."},{"key":"62_CR43","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1109\/DEXA.2008.12","volume-title":"Proceedings of the 2008 19th International Conference on Database and Expert Systems Application","author":"T. Weninger","year":"2008","unstructured":"Weninger, T., Hsu, W.H.: Text Extraction from the Web via Text-to-Tag Ratio. In: Proceedings of the 2008 19th International Conference on Database and Expert Systems Application, pp. 23\u201328. IEEE Computer Society, Washington, DC (2008), doi:10.1109\/DEXA.2008.12"},{"key":"62_CR44","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1145\/1772690.1772789","volume-title":"Proceedings of the 19th International Conference on World Wide Web","author":"T. Weninger","year":"2010","unstructured":"Weninger, T., Hsu, W.H., Han, J.: CETR: content extraction via tag ratios. In: Proceedings of the 19th International Conference on World Wide Web, pp. 971\u2013980. ACM, New York (2010), doi:10.1145\/1772690.1772789"},{"key":"62_CR45","doi-asserted-by":"crossref","unstructured":"Pasternack, J., Roth, D.: Extracting article text from the web with maximum subsequence segmentation. In: Proceedings of the 18th International Conference on World Wide Web, pp. 971\u2013980 (2009)","DOI":"10.1145\/1526709.1526840"},{"key":"62_CR46","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1145\/1718487.1718542","volume-title":"Proceedings of the Third ACM International Conference on Web Search and Data Mining","author":"C. Kohlsch\u00fctter","year":"2010","unstructured":"Kohlsch\u00fctter, C., Fankhauser, P., Nejdl, W.: Boilerplate detection using shallow text features. In: Proceedings of the Third ACM International Conference on Web Search and Data Mining, pp. 441\u2013450. ACM, New York (2010)"},{"key":"62_CR47","volume-title":"Information Retrieval","author":"C.J. Rijsbergen van","year":"1979","unstructured":"van Rijsbergen, C.J.: Information Retrieval, 2nd edn. Butterworth-Heinemann, Newton, MA, USA (1979)","edition":"2"},{"key":"62_CR48","unstructured":"Baroni, M., Chantree, F., Kilgarriff, A., Sharoff, S.: Cleaneval: a Competition for Cleaning Web Pages"},{"key":"62_CR49","unstructured":"Schmid, H.: TreeTagger - a language independent part-of-speech tagger, \n                    \n                      http:\/\/www.ims.uni-stuttgart.de\/projekte\/corplex\/TreeTagger\/\n                    \n                    \n                   (accessed March 10, 2011)"}],"container-title":["Lecture Notes in Computer Science","Active Media Technology"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-35236-2_62","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,8]],"date-time":"2019-05-08T20:35:34Z","timestamp":1557347734000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-35236-2_62"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642352355","9783642352362"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-35236-2_62","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}