@inbook{45882, author = {{Bäumer, Frederik Simon and Chen, Wei-Fan and Geierhos, Michaela and Kersting, Joschka and Wachsmuth, Henning}}, booktitle = {{On-The-Fly Computing -- Individualized IT-services in dynamic markets}}, editor = {{Haake, Claus-Jochen and Meyer auf der Heide, Friedhelm and Platzner, Marco and Wachsmuth, Henning and Wehrheim, Heike}}, pages = {{65--84}}, publisher = {{Heinz Nixdorf Institut, Universität Paderborn}}, title = {{{Dialogue-based Requirement Compensation and Style-adjusted Data-to-text Generation}}}, doi = {{10.5281/zenodo.8068456}}, volume = {{412}}, year = {{2023}}, } @inproceedings{31054, abstract = {{This paper aims at discussing past limitations set in sentiment analysis research regarding explicit and implicit mentions of opinions. Previous studies have regularly neglected this question in favor of methodical research on standard-datasets. Furthermore, they were limited to linguistically less-diverse domains, such as commercial product reviews. We face this issue by annotating a German-language physician review dataset that contains numerous implicit, long, and complex statements that indicate aspect ratings, such as the physician’s friendliness. We discuss the nature of implicit statements and present various samples to illustrate the challenge described.}}, author = {{Kersting, Joschka and Bäumer, Frederik Simon}}, booktitle = {{Proceedings of the Fourteenth International Conference on Pervasive Patterns and Applications (PATTERNS 2022): Special Track AI-DRSWA: Maturing Artificial Intelligence - Data Science for Real-World Applications}}, editor = {{Kersting, Joschka}}, keywords = {{Sentiment analysis, Natural language processing, Aspect phrase extraction}}, location = {{Barcelona, Spain}}, pages = {{5--9}}, publisher = {{IARIA}}, title = {{{Implicit Statements in Healthcare Reviews: A Challenge for Sentiment Analysis}}}, year = {{2022}}, } @inbook{17347, abstract = {{Peer-to-Peer news portals allow Internet users to write news articles and make them available online to interested readers. Despite the fact that authors are free in their choice of topics, there are a number of quality characteristics that an article must meet before it is published. In addition to meaningful titles, comprehensibly written texts and meaning- ful images, relevant tags are an important criteria for the quality of such news. In this case study, we discuss the challenges and common mistakes that Peer-to-Peer reporters face when tagging news and how incorrect information can be corrected through the orchestration of existing Natu- ral Language Processing services. Lastly, we use this illustrative example to give insight into the challenges of dealing with bottom-up taxonomies.}}, author = {{Bäumer, Frederik Simon and Kersting, Joschka and Buff, Bianca and Geierhos, Michaela}}, booktitle = {{Information and Software Technologies}}, editor = {{Audrius, Lopata and Rita, Butkienė and Daina, Gudonienė and Vilma, Sukackė}}, location = {{Kaunas, Litauen}}, pages = {{368----382}}, publisher = {{Springer}}, title = {{{Tag Me If You Can: Insights into the Challenges of Supporting Unrestricted P2P News Tagging}}}, doi = {{https://doi.org/10.1007/978-3-030-59506-7_30}}, volume = {{1283}}, year = {{2020}}, } @inproceedings{18686, author = {{Kersting, Joschka and Bäumer, Frederik Simon}}, booktitle = {{PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON APPLIED COMPUTING 2020}}, keywords = {{Software Requirements, Natural Language Processing, Transfer Learning, On-The-Fly Computing}}, location = {{Lisbon, Portugal}}, pages = {{119----123}}, publisher = {{IADIS}}, title = {{{SEMANTIC TAGGING OF REQUIREMENT DESCRIPTIONS: A TRANSFORMER-BASED APPROACH}}}, year = {{2020}}, } @misc{8312, author = {{Bäumer, Frederik Simon and Geierhos, Michaela}}, booktitle = {{encyclopedia.pub}}, keywords = {{OTF Computing, Natural Language Processing, Requirements Engineering}}, publisher = {{MDPI}}, title = {{{Requirements Engineering in OTF-Computing}}}, year = {{2019}}, } @article{8424, abstract = {{The vision of On-the-Fly (OTF) Computing is to compose and provide software services ad hoc, based on requirement descriptions in natural language. Since non-technical users write their software requirements themselves and in unrestricted natural language, deficits occur such as inaccuracy and incompleteness. These deficits are usually met by natural language processing methods, which have to face special challenges in OTF Computing because maximum automation is the goal. In this paper, we present current automatic approaches for solving inaccuracies and incompletenesses in natural language requirement descriptions and elaborate open challenges. In particular, we will discuss the necessity of domain-specific resources and show why, despite far-reaching automation, an intelligent and guided integration of end users into the compensation process is required. In this context, we present our idea of a chat bot that integrates users into the compensation process depending on the given circumstances. }}, author = {{Bäumer, Frederik Simon and Kersting, Joschka and Geierhos, Michaela}}, issn = {{2073-431X}}, journal = {{Computers}}, keywords = {{Inaccuracy Detection, Natural Language Software Requirements, Chat Bot}}, location = {{Vilnius, Lithuania}}, number = {{1}}, publisher = {{MDPI AG, Basel, Switzerland}}, title = {{{Natural Language Processing in OTF Computing: Challenges and the Need for Interactive Approaches}}}, doi = {{10.3390/computers8010022}}, volume = {{8}}, year = {{2019}}, } @inproceedings{8532, author = {{Bäumer, Frederik Simon and Buff, Bianca and Geierhos, Michaela}}, booktitle = {{DHd 2019 Digital Humanities: multimedial & multimodal. Konferenzabstracts}}, editor = {{Sahle, Patrick}}, isbn = {{978-3-00-062166-6}}, location = {{Mainz and Frankfurt am Main, Germany}}, pages = {{192--193}}, publisher = {{Zenodo}}, title = {{{Potentielle Privatsphäreverletzungen aufdecken und automatisiert sichtbar machen}}}, doi = {{10.5281/zenodo.2596095}}, year = {{2019}}, } @inproceedings{9613, abstract = {{The ability to openly evaluate products, locations and services is an achievement of the Web 2.0. It has never been easier to inform oneself about the quality of products or services and possible alternatives. Forming one’s own opinion based on the impressions of other people can lead to better experiences. However, this presupposes trust in one’s fellows as well as in the quality of the review platforms. In previous work on physician reviews and the corresponding websites, it was observed that there occurs faulty behavior by some reviewers and there were noteworthy differences in the technical implementation of the portals and in the efforts of site operators to maintain high quality reviews. These experiences raise new questions regarding what trust means on review platforms, how trust arises and how easily it can be destroyed.}}, author = {{Kersting, Joschka and Bäumer, Frederik Simon and Geierhos, Michaela}}, booktitle = {{Proceedings of the 4th International Conference on Internet of Things, Big Data and Security}}, editor = {{Ramachandran, Muthu and Walters, Robert and Wills, Gary and Méndez Muñoz, Víctor and Chang, Victor}}, isbn = {{978-989-758-369-8}}, keywords = {{Trust, Physician Reviews, Network Analysis}}, location = {{Heraklion, Greece}}, pages = {{147--155}}, publisher = {{SCITEPRESS}}, title = {{{In Reviews We Trust: But Should We? Experiences with Physician Review Websites}}}, year = {{2019}}, } @inproceedings{12946, author = {{Bäumer, Frederik Simon and Buff, Bianca}}, booktitle = {{Proceedings of the 8th International Conference on Data Science, Technology and Applications}}, isbn = {{9789897583773}}, title = {{{How to Boost Customer Relationship Management via Web Mining Benefiting from the Glass Customer’s Openness}}}, doi = {{10.5220/0007828301290136}}, year = {{2019}}, } @inbook{2322, abstract = {{The vision of On-The-Fly Computing is an automatic composition of existing software services. Based on natural language software descriptions, end users will receive compositions tailored to their needs. For this reason, the quality of the initial software service description strongly determines whether a software composition really meets the expectations of end users. In this paper, we expose open NLP challenges needed to be faced for service composition in On-The-Fly Computing.}}, author = {{Bäumer, Frederik Simon and Geierhos, Michaela}}, booktitle = {{Proceedings of the 23rd International Conference on Natural Language and Information Systems}}, editor = {{Silberztein, Max and Atigui, Faten and Kornyshova, Elena and Métais, Elisabeth and Meziane, Farid }}, isbn = {{978-3-319-91946-1}}, keywords = {{Requirements Extraction, Temporal Reordering of Software Functions, Inaccuracy Compensation}}, location = {{Paris, France}}, pages = {{509--513}}, publisher = {{Springer}}, title = {{{How to Deal with Inaccurate Service Descriptions in On-The-Fly Computing: Open Challenges}}}, doi = {{10.1007/978-3-319-91947-8_53}}, volume = {{10859}}, year = {{2018}}, } @inbook{4338, abstract = {{Physician review websites are known around the world. Patients review the subjectively experienced quality of medical services supplied to them and publish an overall rating on the Internet, where quantitative grades and qualitative texts come together. On the one hand, these new possibilities reduce the imbalance of power between health care providers and patients, but on the other hand, they can also damage the usually very intimate relationship between health care providers and patients. Review websites must meet these requirements with a high level of responsibility and service quality. In this paper, we look at the situation in Lithuania: Especially, we are interested in the available possibilities of evaluation and interaction, and the quality of a particular review website measured against the available data. We thereby identify quality weaknesses and lay the foundation for future research.}}, author = {{Bäumer, Frederik Simon and Kersting, Joschka and Kuršelis, Vytautas and Geierhos, Michaela}}, booktitle = {{Communications in Computer and Information Science}}, editor = {{Damaševičius, Robertas and Vasiljevienė, Giedrė}}, isbn = {{9783319999715}}, issn = {{1865-0929}}, keywords = {{Lithuanian physician review websites, Medical service ratings}}, location = {{Vilnius, Lithuania}}, pages = {{43--58}}, publisher = {{Springer}}, title = {{{Rate Your Physician: Findings from a Lithuanian Physician Rating Website}}}, doi = {{10.1007/978-3-319-99972-2_4}}, volume = {{920}}, year = {{2018}}, } @inproceedings{4339, abstract = {{On-The-Fly Computing is the vision of covering software needs of end users by fully-automatic compositions of existing software services. End users will receive so-called service compositions tailored to their very individual needs, based on natural language software descriptions. This everyday language may contain inaccuracies and incompleteness, which are well-known challenges in requirements engineering. In addition to existing approaches that try to automatically identify and correct these deficits, there are also new trends to involve users more in the elaboration and refinement process. In this paper, we present the relevant state of the art in the field of automated detection and compensation of multiple inaccuracies in natural language service descriptions and name open challenges needed to be tackled in NL-based software service composition. }}, author = {{Bäumer, Frederik Simon and Geierhos, Michaela}}, booktitle = {{Proceedings of the 24th International Conference on Information and Software Technologies (ICIST 2018)}}, editor = {{Damaševičius, Robertas and Vasiljevienė, Giedrė}}, isbn = {{9783319999715}}, issn = {{1865-0929}}, keywords = {{Inaccuracy detection, Natural language software requirements}}, location = {{Vilnius, Lithuania}}, pages = {{559--570}}, publisher = {{Springer}}, title = {{{NLP in OTF Computing: Current Approaches and Open Challenges}}}, doi = {{10.1007/978-3-319-99972-2_46}}, volume = {{920}}, year = {{2018}}, } @inproceedings{4341, author = {{Bäumer, Frederik Simon and Geierhos, Michaela}}, booktitle = {{European Conference on Data Analysis 2018: Multidisciplinary Facets of Data Science - Book of Abstracts}}, location = {{Paderborn, Germany}}, title = {{{Text Broom: A ML-based Tool to Detect and Highlight Privacy Breaches in Physician Reviews: An Insight into Our Current Work}}}, year = {{2018}}, } @inproceedings{4349, abstract = {{Physician Review Websites allow users to evaluate their experiences with health services. As these evaluations are regularly contextualized with facts from users’ private lives, they often accidentally disclose personal information on the Web. This poses a serious threat to users’ privacy. In this paper, we report on early work in progress on “Text Broom”, a tool to detect privacy breaches in user-generated texts. For this purpose, we conceptualize a pipeline which combines methods of Natural Language Processing such as Named Entity Recognition, linguistic patterns and domain-specific Machine Learning approaches which have the potential to recognize privacy violations with wide coverage. A prototypical web application is openly accesible.}}, author = {{Bäumer, Frederik Simon and Kersting, Joschka and Orlikowski, Matthias and Geierhos, Michaela}}, booktitle = {{Proceedings of the Posters and Demos Track of the 14th International Conference on Semantic Systems co-located with the 14th International Conference on Semantic Systems (SEMANTiCS 2018)}}, editor = {{Khalili, Ali and Koutraki, Maria}}, issn = {{1613-0073}}, keywords = {{Detection of Privacy Violations, Physician Reviews}}, location = {{Vienna, Austria}}, publisher = {{CEUR-WS.org}}, title = {{{Towards a Multi-Stage Approach to Detect Privacy Breaches in Physician Reviews}}}, volume = {{2198}}, year = {{2018}}, } @inproceedings{44, abstract = {{Natural language software requirements descriptions enable end users to formulate their wishes and expectations for a future software product without much prior knowledge in requirements engineering. However, these descriptions are susceptible to linguistic inaccuracies such as ambiguities and incompleteness that can harm the development process. There is a number of software solutions that can detect deficits in requirements descriptions and partially solve them, but they are often hard to use and not suitable for end users. For this reason, we develop a software system that helps end-users to create unambiguous and complete requirements descriptions by combining existing expert tools and controlling them using automatic compensation strategies. In order to recognize the necessity of individual compensation methods in the descriptions, we have developed linguistic indicators, which we present in this paper. Based on these indicators, the whole text analysis pipeline is ad-hoc configured and thus adapted to the individual circumstances of a requirements description.}}, author = {{Bäumer, Frederik Simon and Geierhos, Michaela}}, booktitle = {{Proceedings of the 51st Hawaii International Conference on System Sciences}}, isbn = {{978-0-9981331-1-9}}, keywords = {{Software Product Lines: Engineering, Services, and Management, Ambiguities, Incompleteness, Natural Language Processing, Software Requirements}}, location = {{Big Island, Waikoloa Village}}, pages = {{5746--5755}}, title = {{{Flexible Ambiguity Resolution and Incompleteness Detection in Requirements Descriptions via an Indicator-based Configuration of Text Analysis Pipelines}}}, doi = {{10125/50609}}, year = {{2018}}, } @inproceedings{1181, abstract = {{The main idea in On-The-Fly Computing is to automatically compose existing software services according to the wishes of end-users. However, since user requirements are often ambiguous, vague and incomplete, the selection and composition of suitable software services is a challanging task. In this paper, we present our current approach to improve requirement descriptions before they are used for software composition. This procedure is fully automated, but also has limitations, for example, if necessary information is missing. In addition, and in response to the limitations, we provide insights into our above-mentioned current work that combines the existing optimization approach with a chatbot solution.}}, author = {{Bäumer, Frederik Simon and Geierhos, Michaela}}, booktitle = {{Joint Proceedings of REFSQ-2018 Workshops, Doctoral Symposium, Live Studies Track, and Poster Track co-located with the 23rd International Conference on Requirements Engineering: Foundation for Software Quality (REFSQ 2018)}}, editor = {{Schmid, Klaus and Spoletini, Paola and Ben Charrada, Eya and Chisik, Yoram and Dalpiaz, Fabiano and Ferrari, Alessio and Forbrig, Peter and Franch, Xavier and Kirikova, Marite and Madhavji, Nazim and Palomares, Cristina and Ralyté, Jolita and Sabetzadeh, Mehrdad and Sawyer, Pete and van der Linden, Dirk and Zamansky, Anna}}, issn = {{1613-0073}}, location = {{Utrecht, The Netherlands}}, publisher = {{CEUR-WS.org}}, title = {{{How to Deal with Inaccurate Service Requirements? Insights in Our Current Approach and New Ideas}}}, volume = {{2075}}, year = {{2018}}, } @inproceedings{1182, abstract = {{Natural language requirement descriptions are often unstructured, contradictory and incomplete and are therefore challenging for automatic processing. Although many of these deficits can be compensated by means of Natural Language Processing, there still remain cases where interaction with end-users is necessary for clarification. In this paper, we present our idea of using chatbot technology to establish end-user communication in order to support the automatic compensation of some deficits in natural language requirement descriptions.}}, author = {{Friesen, Edwin and Bäumer, Frederik Simon and Geierhos, Michaela}}, booktitle = {{Joint Proceedings of REFSQ-2018 Workshops, Doctoral Symposium, Live Studies Track, and Poster Track co-located with the 23rd International Conference on Requirements Engineering: Foundation for Software Quality (REFSQ 2018)}}, editor = {{Schmid, Klaus and Spoletini, Paola and Ben Charrada, Eya and Chisik, Yoram and Dalpiaz, Fabiano and Ferrari, Alessio and Forbrig, Peter and Franch, Xavier and Kirikova, Marite and Madhavji, Nazim and Palomares, Cristina and Ralyté, Jolita and Sabetzadeh, Mehrdad and Sawyer, Pete and van der Linden, Dirk and Zamansky, Anna }}, issn = {{1613-0073}}, location = {{Utrecht, The Netherlands}}, publisher = {{CEUR-WS.org}}, title = {{{CORDULA: Software Requirements Extraction Utilizing Chatbot as Communication Interface}}}, volume = {{2075}}, year = {{2018}}, } @inproceedings{1183, abstract = {{As our world grows in complexity, companies and employees alike need, more than ever before, solutions tailored to their exact needs. Since such tools cannot always be purchased off-the-shelf and need to be designed from the ground up, developers rely on software requirements. In this paper, we present our vision of a syntactic rule-based extraction tool for software requirements specification documents. In contrast to other methods, our tool will allow stakeholders to express their needs and wishes in unfiltered natural language, which we believe is essential for non-expert users.}}, author = {{Caron, Matthew and Bäumer, Frederik Simon and Geierhos, Michaela}}, booktitle = {{Joint Proceedings of REFSQ-2018 Workshops, Doctoral Symposium, Live Studies Track, and Poster Track co-located with the 23rd International Conference on Requirements Engineering: Foundation for Software Quality (REFSQ 2018)}}, editor = {{Schmid, Klaus and Spoletini, Paola and Ben Charrada, Eya and Chisik, Yoram and Dalpiaz, Fabiano and Ferrari, Alessio and Forbrig, Peter and Franch, Xavier and Kirikova, Marite and Madhavji, Nazim and Palomares, Cristina and Ralyté, Jolita and Sabetzadeh, Mehrdad and Sawyer, Pete and van der Linden, Dirk and Zamansky, Anna}}, issn = {{1613-0073}}, location = {{Utrecht, The Netherlands}}, publisher = {{CEUR-WS.org}}, title = {{{Back to Basics: Extracting Software Requirements with a Syntactic Approach}}}, volume = {{2075}}, year = {{2018}}, } @inbook{1161, abstract = {{Consulting a physician was long regarded as an intimate and private matter. The physician-patient relationship was perceived as sensitive and trustful. Nowadays, there is a change, as medical procedures and physicians consultations are reviewed like other services on the Internet. To allay user’s privacy doubts, physician review websites assure anonymity and the protection of private data. However, there are hundreds of reviews that reveal private information and hence enable physicians or the public to identify patients. Thus, we draw attention to the cases when de-anonymization is possible. We therefore introduce an approach that highlights private information in physician reviews for users to avoid an accidental disclosure. For this reason, we combine established natural-language-processing techniques such as named entity recognition as well as handcrafted patterns to achieve a high detection accuracy. That way, we can help websites to increase privacy protection by recognizing and uncovering apparently uncritical information in user-generated texts.}}, author = {{Bäumer, Frederik Simon and Grote, Nicolai and Kersting, Joschka and Geierhos, Michaela}}, booktitle = {{Information and Software Technologies: 23rd International Conference, ICIST 2017, Druskininkai, Lithuania, October 12–14, 2017, Proceedings}}, editor = {{Damaševičius, Robertas and Mikašytė, Víctor}}, isbn = {{978-3-319-67641-8}}, keywords = {{Physician Reviews, User Privacy, Nocuous Data Exposure}}, location = {{Druskininkai, Lithuania}}, pages = {{77--89}}, publisher = {{Springer}}, title = {{{Privacy Matters: Detecting Nocuous Patient Data Exposure in Online Physician Reviews}}}, doi = {{10.1007/978-3-319-67642-5_7}}, volume = {{756}}, year = {{2017}}, } @inbook{93, abstract = {{In recent years, there has been a proliferation of technological developments that incorporate processing of human language. Hardware and software can be specialized for designated subject areas, and computational devices are designed for a widening variety of applications. At the same time, new areas and applications are emerging by demanding intelligent technology enhanced by the processing of human language. These new applications often perform tasks which handle information, and they have a capacity to reason, using both formal and human language. Many sub-areas of Artificial Intelligence demand integration of Natural Language Processing, at least to some degree. Furthermore, technologies require coverage of known as well as unknown agents, and tasks with potential variations. All of this takes place in environments with unknown factors. The book covers theoretical work, advanced applications, approaches, and techniques for computational models of information, reasoning systems, and presentation in language. The book promotes work on intelligent natural language processing and related models of information, thought, reasoning, and other cognitive processes. The topics covered by the chapters prompt further research and developments of advanced systems in the areas of logic, computability, computational linguistics, cognitive science, neuroscience of language, robotics, and artificial intelligence, among others.}}, author = {{Geierhos, Michaela and Bäumer, Frederik Simon}}, booktitle = {{Partiality and Underspecification in Information, Languages, and Knowledge}}, editor = {{Christiansen, Henning and Jiménez-López, M. Dolores and Loukanova, Roussanka and Moss, Lawrence S.}}, isbn = {{978-1- 4438-7947-7}}, pages = {{65--108}}, publisher = {{Cambridge Scholars Publishing}}, title = {{{Guesswork? Resolving Vagueness in User-Generated Software Requirements}}}, year = {{2017}}, }