[{"author":[{"first_name":"Joschka","last_name":"Kersting","id":"58701","full_name":"Kersting, Joschka"}],"date_created":"2023-05-02T12:54:00Z","supervisor":[{"first_name":"Michaela","id":"42496","full_name":"Geierhos, Michaela","orcid":"0000-0002-8180-5606","last_name":"Geierhos"}],"publisher":"Universität der Bundeswehr München ","date_updated":"2023-07-03T12:29:50Z","title":"Identifizierung quantifizierbarer Bewertungsinhalte und -kategorien mittels Text Mining","related_material":{"link":[{"url":"https://athene-forschung.unibw.de/145003","relation":"supplementary_material"}]},"publication_status":"published","page":"208","citation":{"bibtex":"@book{Kersting_2023, place={Neubiberg}, title={Identifizierung quantifizierbarer Bewertungsinhalte und -kategorien mittels Text Mining}, publisher={Universität der Bundeswehr München }, author={Kersting, Joschka}, year={2023} }","mla":"Kersting, Joschka. <i>Identifizierung quantifizierbarer Bewertungsinhalte und -kategorien mittels Text Mining</i>. Universität der Bundeswehr München , 2023.","short":"J. Kersting, Identifizierung quantifizierbarer Bewertungsinhalte und -kategorien mittels Text Mining, Universität der Bundeswehr München , Neubiberg, 2023.","apa":"Kersting, J. (2023). <i>Identifizierung quantifizierbarer Bewertungsinhalte und -kategorien mittels Text Mining</i>. Universität der Bundeswehr München .","chicago":"Kersting, Joschka. <i>Identifizierung quantifizierbarer Bewertungsinhalte und -kategorien mittels Text Mining</i>. Neubiberg: Universität der Bundeswehr München , 2023.","ieee":"J. Kersting, <i>Identifizierung quantifizierbarer Bewertungsinhalte und -kategorien mittels Text Mining</i>. Neubiberg: Universität der Bundeswehr München , 2023.","ama":"Kersting J. <i>Identifizierung quantifizierbarer Bewertungsinhalte und -kategorien mittels Text Mining</i>. Universität der Bundeswehr München ; 2023."},"place":"Neubiberg","year":"2023","department":[{"_id":"579"},{"_id":"7"}],"user_id":"58701","_id":"44323","project":[{"name":"SFB 901: SFB 901","_id":"1","grant_number":"160364472"},{"_id":"3","name":"SFB 901 - B: SFB 901 - Project Area B"},{"name":"SFB 901 - B1: SFB 901 - Subproject B1","_id":"9","grant_number":"160364472"}],"language":[{"iso":"ger"}],"type":"dissertation","status":"public","abstract":[{"lang":"eng","text":"Reading between the lines has so far been reserved for humans. The present dissertation addresses this research gap using machine learning methods.\r\nImplicit expressions are not comprehensible by computers and cannot be localized in the text. However, many texts arise on interpersonal topics that, unlike commercial evaluation texts, often imply information only by means of longer phrases. Examples are the kindness and the attentiveness of a doctor, which are only paraphrased (“he didn’t even look me in the eye”). The analysis of such data, especially the identification and localization of implicit statements, is a research gap (1). This work uses so-called Aspect-based Sentiment Analysis as a method for this purpose. It remains open how the aspect categories to be extracted can be discovered and thematically delineated based on the data (2). Furthermore, it is not yet explored how a collection of tools should look like, with which implicit phrases can be identified and thus made explicit\r\n(3). Last, it is an open question how to correlate the identified phrases from the text data with other data, including the investigation of the relationship between quantitative scores (e.g., school grades) and the thematically related text (4). Based on these research gaps, the research question is posed as follows: Using text mining methods, how can implicit rating content be properly interpreted and thus made explicit before it is automatically categorized and quantified?\r\nThe uniqueness of this dissertation is based on the automated recognition of implicit linguistic statements alongside explicit statements. These are identified in unstructured text data so that features expressed only in the text can later be compared across data sources, even though they were not included in rating categories such as stars or school grades. German-language physician ratings from websites in three countries serve as the sample domain. The solution approach consists of data creation, a pipeline for text processing and analyses based on this. In the data creation, aspect classes are identified and delineated across platforms and marked in text data. This results in six datasets with over 70,000 annotated sentences and detailed guidelines. The models that were created based on the training data extract and categorize the aspects. In addition, the sentiment polarity and the evaluation weight, i. e., the importance of each phrase, are determined. The models, which are combined in a pipeline, are used in a prototype in the form of a web application. The analyses built on the pipeline quantify the rating contents by linking the obtained information with further data, thus allowing new insights.\r\nAs a result, a toolbox is provided to identify quantifiable rating content and categories using text mining for a sample domain. This is used to evaluate the approach, which in principle can also be adapted to any other domain."}]},{"language":[{"iso":"ger"}],"project":[{"_id":"1","name":"SFB 901"},{"name":"SFB 901 - Project Area B","_id":"3"},{"name":"SFB 901 - Subproject B1","_id":"9"}],"_id":"13435","user_id":"477","department":[{"_id":"36"},{"_id":"1"},{"_id":"579"}],"status":"public","type":"bachelorsthesis","title":"Requirements Engineering im OTF-Computing: Informationsextraktion und Unvollständigkeitskompensation mittels domänenspezifischer Wissensbasis","date_updated":"2022-01-06T06:51:36Z","publisher":"Universität Paderborn","author":[{"last_name":"Friesen","full_name":"Friesen, Edwin","first_name":"Edwin"}],"supervisor":[{"last_name":"Hüllermeier","id":"48129","full_name":"Hüllermeier, Eyke","first_name":"Eyke"},{"full_name":"Geierhos, Michaela","id":"42496","last_name":"Geierhos","orcid":"0000-0002-8180-5606","first_name":"Michaela"}],"date_created":"2019-09-20T14:58:49Z","year":"2019","citation":{"chicago":"Friesen, Edwin. <i>Requirements Engineering im OTF-Computing: Informationsextraktion und Unvollständigkeitskompensation mittels domänenspezifischer Wissensbasis</i>. Universität Paderborn, 2019.","ieee":"E. Friesen, <i>Requirements Engineering im OTF-Computing: Informationsextraktion und Unvollständigkeitskompensation mittels domänenspezifischer Wissensbasis</i>. Universität Paderborn, 2019.","ama":"Friesen E. <i>Requirements Engineering im OTF-Computing: Informationsextraktion und Unvollständigkeitskompensation mittels domänenspezifischer Wissensbasis</i>. Universität Paderborn; 2019.","mla":"Friesen, Edwin. <i>Requirements Engineering im OTF-Computing: Informationsextraktion und Unvollständigkeitskompensation mittels domänenspezifischer Wissensbasis</i>. Universität Paderborn, 2019.","bibtex":"@book{Friesen_2019, title={Requirements Engineering im OTF-Computing: Informationsextraktion und Unvollständigkeitskompensation mittels domänenspezifischer Wissensbasis}, publisher={Universität Paderborn}, author={Friesen, Edwin}, year={2019} }","short":"E. Friesen, Requirements Engineering im OTF-Computing: Informationsextraktion und Unvollständigkeitskompensation mittels domänenspezifischer Wissensbasis, Universität Paderborn, 2019.","apa":"Friesen, E. (2019). <i>Requirements Engineering im OTF-Computing: Informationsextraktion und Unvollständigkeitskompensation mittels domänenspezifischer Wissensbasis</i>. Universität Paderborn."}},{"language":[{"iso":"ger"}],"_id":"89","project":[{"name":"SFB 901","_id":"1"},{"name":"SFB 901 - Subprojekt B1","_id":"9"},{"name":"SFB 901 - Project Area B","_id":"3"}],"department":[{"_id":"579"},{"_id":"36"},{"_id":"1"}],"user_id":"14931","abstract":[{"text":"The vision of OTF Computing is to have the software needs of end users in the future covered by an automatic composition of existing software services. Here we focus on natural language software requirements that end users formulate and submit to OTF providers as requirement specifications. These requirements serve as the sole foundation for the composition of software; but they can be inaccurate and incomplete. Up to now, software developers have identified and corrected these deficits by using a bidirectional consolidation process. However, this type of quality assurance is no longer included in OTF Computing - the classic consolidation process is dropped. This is where this work picks up, dealing with the inaccuracies of freely formulated software design requirements. To do this, we developed the CORDULA (Compensation of Requirements Descriptions Using Linguistic Analysis) system that recognizes and compensates for language deficiencies (e.g., ambiguity, vagueness and incompleteness) in requirements written by inexperienced end users. CORDULA supports the search for suitable software services that can be combined in a composition by transferring requirement specifications into canonical core functionalities. This dissertation provides the first-ever method for holistically recording and improving language deficiencies in user-generated requirement specifications by dealing with ambiguity, incompleteness and vagueness in parallel and in sequence.","lang":"eng"}],"status":"public","type":"dissertation","title":"Indikatorbasierte Erkennung und Kompensation von ungenauen und unvollständig beschriebenen Softwareanforderungen","doi":"10.17619/UNIPB/1-157","publisher":"Universität Paderborn","date_updated":"2022-01-06T07:04:05Z","date_created":"2017-10-17T12:41:08Z","author":[{"first_name":"Frederik Simon","last_name":"Bäumer","id":"38837","full_name":"Bäumer, Frederik Simon"}],"supervisor":[{"orcid":"0000-0002-8180-5606","last_name":"Geierhos","id":"42496","full_name":"Geierhos, Michaela","first_name":"Michaela"}],"year":"2017","citation":{"bibtex":"@book{Bäumer_2017, title={Indikatorbasierte Erkennung und Kompensation von ungenauen und unvollständig beschriebenen Softwareanforderungen}, DOI={<a href=\"https://doi.org/10.17619/UNIPB/1-157\">10.17619/UNIPB/1-157</a>}, publisher={Universität Paderborn}, author={Bäumer, Frederik Simon}, year={2017} }","mla":"Bäumer, Frederik Simon. <i>Indikatorbasierte Erkennung und Kompensation von ungenauen und unvollständig beschriebenen Softwareanforderungen</i>. Universität Paderborn, 2017, doi:<a href=\"https://doi.org/10.17619/UNIPB/1-157\">10.17619/UNIPB/1-157</a>.","short":"F.S. Bäumer, Indikatorbasierte Erkennung und Kompensation von ungenauen und unvollständig beschriebenen Softwareanforderungen, Universität Paderborn, 2017.","apa":"Bäumer, F. S. (2017). <i>Indikatorbasierte Erkennung und Kompensation von ungenauen und unvollständig beschriebenen Softwareanforderungen</i>. Universität Paderborn. <a href=\"https://doi.org/10.17619/UNIPB/1-157\">https://doi.org/10.17619/UNIPB/1-157</a>","ama":"Bäumer FS. <i>Indikatorbasierte Erkennung und Kompensation von ungenauen und unvollständig beschriebenen Softwareanforderungen</i>. Universität Paderborn; 2017. doi:<a href=\"https://doi.org/10.17619/UNIPB/1-157\">10.17619/UNIPB/1-157</a>","ieee":"F. S. Bäumer, <i>Indikatorbasierte Erkennung und Kompensation von ungenauen und unvollständig beschriebenen Softwareanforderungen</i>. Universität Paderborn, 2017.","chicago":"Bäumer, Frederik Simon. <i>Indikatorbasierte Erkennung und Kompensation von ungenauen und unvollständig beschriebenen Softwareanforderungen</i>. Universität Paderborn, 2017. <a href=\"https://doi.org/10.17619/UNIPB/1-157\">https://doi.org/10.17619/UNIPB/1-157</a>."}}]