@inproceedings{25245, author = {{Baeumer, Frederik Simon and Dollmann, Markus and Geierhos, Michaela}}, booktitle = {{Proceedings of the 2nd ACM SIGSOFT International Workshop on App Market Analytics}}, editor = {{Sarro, Federica and Shihab, Emad and Nagappan, Meiyappan and Platenius, Marie Christin and Kaimann, Daniel}}, pages = {{19--25}}, publisher = {{ACM}}, title = {{{Studying Software Descriptions in SourceForge and App Stores for a better Understanding of real-life Requirements}}}, year = {{2017}}, } @inproceedings{1156, abstract = {{In this paper, we present an IoT architecture which handles stream sensor data of air pollution. Particle pollution is known as a serious threat to human health. Along with developments in the use of wireless sensors and the IoT, we propose an architecture that flexibly measures and processes stream data collected in real-time by movable and low-cost IoT sensors. Thus, it enables a wide-spread network of wireless sensors that can follow changes in human behavior. Apart from stating reasons for the need of such a development and its requirements, we provide a conceptual design as well as a technological design of such an architecture. The technological design consists of Kaa and Apache Storm which can collect air pollution information in real-time and solve various problems to process data such as missing data and synchronization. This enables us to add a simulation in which we provide issues that might come up when having our architecture in use. Together with these issues, we state r easons for choosing specific modules among candidates. Our architecture combines wireless sensors with the Kaa IoT framework, an Apache Kafka pipeline and an Apache Storm Data Stream Management System among others. We even provide open-government data sets that are freely available.}}, author = {{Kersting, Joschka and Geierhos, Michaela and Jung, Hanmin and Kim, Taehong}}, booktitle = {{Proceedings of the 2nd International Conference on Internet of Things, Big Data and Security}}, editor = {{Ramachandran, Muthu and Méndez Muñoz, Víctor and Kantere, Verena and Wills, Gary and Walters, Robert and Chang, Victor}}, isbn = {{978-989-758-245-5}}, keywords = {{Wireless Sensor Network, Internet of Things, Stream Data, Air Pollution, DSMS, Real-time Data Processing}}, location = {{Porto, Portugal}}, pages = {{117--124}}, publisher = {{SCITEPRESS}}, title = {{{Internet of Things Architecture for Handling Stream Air Pollution Data}}}, doi = {{10.5220/0006354801170124}}, year = {{2017}}, } @inproceedings{1158, abstract = {{In this paper, we present the annotation challenges we have encountered when working on a historical language that was undergoing elaboration processes. We especially focus on syntactic ambiguity and gradience in Middle Low German, which causes uncertainty to some extent. Since current annotation tools consider construction contexts and the dynamics of the grammaticalization only partially, we plan to extend CorA – a web-based annotation tool for historical and other non-standard language data – to capture elaboration phenomena and annotator unsureness. Moreover, we seek to interactively learn morphological as well as syntactic annotations.}}, author = {{Seemann, Nina and Merten, Marie-Luis and Geierhos, Michaela and Tophinke, Doris and Hüllermeier, Eyke}}, booktitle = {{Proceedings of the Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature}}, location = {{Vancouver, BC, Canada}}, pages = {{40--45}}, publisher = {{Association for Computational Linguistics (ACL)}}, title = {{{Annotation Challenges for Reconstructing the Structural Elaboration of Middle Low German}}}, doi = {{10.18653/v1/W17-2206}}, year = {{2017}}, } @inbook{1159, abstract = {{In this paper, we present a search solution that makes local news information easily accessible. In the era of fake news, we provide an approach for accessing news information through opinion mining. This enables users to view news on the same topics from different web sources. By applying sentiment analysis on social media posts, users can better understand how issues are captured and see people’s reactions. Therefore, we provide a local search service that first localizes news articles, then visualizes their occurrence according to the frequency of mentioned topics on a heatmap and even shows the sentiment score for each text. }}, author = {{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, Vilma}}, isbn = {{978-3-319-67641-8}}, location = {{Druskininkai, Lithuania}}, pages = {{528--538}}, publisher = {{Springer}}, title = {{{Using Sentiment Analysis on Local Up-to-the-Minute News: An Integrated Approach}}}, doi = {{10.1007/978-3-319-67642-5}}, volume = {{756}}, year = {{2017}}, } @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}}, } @inproceedings{57, abstract = {{Users prefer natural language software requirements because of their usability and accessibility. Many approaches exist to elaborate these requirements and to support the users during the elicitation process. But there is a lack of adequate resources, which are needed to train and evaluate approaches for requirement refinement. We are trying to close this gap by using online available software descriptions from SourceForge and app stores. Thus, we present two real-life requirements collections based on online-available software descriptions. Our goal is to show the domain-specific characteristics of content words describing functional requirements. On the one hand, we created a semantic role-labeled requirements set, which we use for requirements classification. On the other hand, we enriched software descriptions with linguistic features and dependencies to provide evidence for the context-awareness of software functionalities. }}, author = {{Bäumer, Frederik Simon and Dollmann, Markus and Geierhos, Michaela}}, booktitle = {{Proceedings of the 2nd ACM SIGSOFT International Workshop on App Market Analytics}}, editor = {{Sarro, Federica and Shihab, Emad and Nagappan, Meiyappan and Platenius, Marie Christin and Kaimann, Daniel}}, isbn = {{978-1-4503-5158-4}}, location = {{Paderborn, Germany}}, pages = {{19--25}}, publisher = {{ACM}}, title = {{{Studying Software Descriptions in SourceForge and App Stores for a better Understanding of real-life Requirements}}}, doi = {{10.1145/3121264.3121269}}, year = {{2017}}, } @phdthesis{89, abstract = {{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.}}, author = {{Bäumer, Frederik Simon}}, publisher = {{Universität Paderborn}}, title = {{{Indikatorbasierte Erkennung und Kompensation von ungenauen und unvollständig beschriebenen Softwareanforderungen}}}, doi = {{10.17619/UNIPB/1-157}}, year = {{2017}}, } @inproceedings{97, abstract = {{Bridging the gap between informal, imprecise, and vague user requirements descriptions and precise formalized specifications is the main task of requirements engineering. Techniques such as interviews or story telling are used when requirements engineers try to identify a user's needs. The requirements specification process is typically done in a dialogue between users, domain experts, and requirements engineers. In our research, we aim at automating the specification of requirements. The idea is to distinguish between untrained users and trained users, and to exploit domain knowledge learned from previous runs of our system. We let untrained users provide unstructured natural language descriptions, while we allow trained users to provide examples of behavioral descriptions. In both cases, our goal is to synthesize formal requirements models similar to statecharts. From requirements specification processes with trained users, behavioral ontologies are learned which are later used to support the requirements specification process for untrained users. Our research method is original in combining natural language processing and search-based techniques for the synthesis of requirements specifications. Our work is embedded in a larger project that aims at automating the whole software development and deployment process in envisioned future software service markets.}}, author = {{van Rooijen, Lorijn and Bäumer, Frederik Simon and Platenius, Marie Christin and Geierhos, Michaela and Hamann, Heiko and Engels, Gregor}}, booktitle = {{2017 IEEE 25th International Requirements Engineering Conference Workshops (REW)}}, isbn = {{978-1-5386-3489-9}}, keywords = {{Software, Unified modeling language, Requirements engineering, Ontologies, Search problems, Natural languages}}, location = {{Lisbon, Portugal}}, pages = {{379--385}}, publisher = {{IEEE}}, title = {{{From User Demand to Software Service: Using Machine Learning to Automate the Requirements Specification Process}}}, doi = {{10.1109/REW.2017.26}}, year = {{2017}}, } @article{1098, abstract = {{An end user generally writes down software requirements in ambiguous expressions using natural language; hence, a software developer attuned to programming language finds it difficult to understand th meaning of the requirements. To solve this problem we define semantic categories for disambiguation and classify/annotate the requirement into the categories by using machine-learning models. We extensively use a language frame closely related to such categories for designing features to overcome the problem of insufficient training data compare to the large number of classes. Our proposed model obtained a micro-average F1-score of 0.75, outperforming the previous model, REaCT.}}, author = {{Kim, Yeong-Su and Lee, Seung-Woo and Dollmann, Markus and Geierhos, Michaela}}, issn = {{2205-8494}}, journal = {{International Journal of Software Engineering for Smart Device}}, keywords = {{Natural Language Processing, Semantic Annotation, Machine Learning}}, number = {{2}}, pages = {{1--6}}, publisher = {{Global Vision School Publication}}, title = {{{Semantic Annotation of Software Requirements with Language Frame}}}, volume = {{4}}, year = {{2017}}, } @inbook{25260, author = {{Geierhos, Michaela}}, booktitle = {{Encyclopedia {\ "a} the business informatics}}, editor = {{Gronau, Norbert and Becker, J {\ "o} rg and Sinz, Elmar and Suhl, L and Leimeister, Jan Marco}}, publisher = {{GITO-Verlag}}, title = {{{Sentiment analysis }}}, year = {{2016}}, } @inbook{25261, author = {{Geierhos, Michaela}}, booktitle = {{Encyclopedia {\ "a} the business informatics}}, editor = {{Gronau, Norbert and Becker, J {\ "o} rg and Sinz, Elmar and Suhl, L and Leimeister, Jan Marco}}, publisher = {{GITO-Verlag}}, title = {{{Webmonitoring}}}, year = {{2016}}, } @inbook{25263, author = {{Geierhos, Michaela}}, booktitle = {{Encyclopedia {\ "a} the business informatics }}, editor = {{Gronau, Norbert and Becker, J {\ "o} rg and Sinz, Elmar and Suhl, L and Leimeister, Jan Marco}}, publisher = {{GITO-Verlag}}, title = {{{Crawler (focused / not focused)}}}, year = {{2016}}, } @inbook{25264, author = {{Geierhos, Michaela}}, booktitle = {{Encyclopedia {\ "a} the business informatics }}, editor = {{Gronau, Norbert and Becker, J {\ "o} rg and Sinz, Elmar and Suhl, L and Leimeister,, Jan Marco}}, publisher = {{GITO-Verlag}}, title = {{{Text Mining}}}, year = {{2016}}, } @inbook{25315, author = {{Baeumer, Frederik Simon and Geierhos, Michaela}}, booktitle = {{Proceedings of the 22nd Conference on Information and Software Technologies (ICIST 2016)}}, editor = {{Dregvaite, Giedre and Damasevicius, Robertas, Robertas}}, isbn = {{978-3-319-46254-7}}, pages = {{549--558}}, publisher = {{Springer International Publishing}}, title = {{{Running Out of Words: How Similar User Stories Can Help to Elaborate Individual Natural Language Requirement Descriptions}}}, volume = {{639}}, year = {{2016}}, } @inproceedings{25317, author = {{Geierhos, Michaela and Baeumer, Frederik Simon}}, booktitle = {{Proceedings of the 21st International Conference on Applications of Natural Language to Information Systems (NLDB 2016)}}, pages = {{37--47}}, publisher = {{Springer}}, title = {{{How to Complete Customer Requirements Using Concept Expansion for Requirement Refinement}}}, volume = {{9612}}, year = {{2016}}, } @inbook{25318, author = {{Stotz, Sophia Charlotte and Geierhos, Michaela}}, booktitle = {{DHd 2016: Modellierung - Vernetzung - Visualisierung. Die Digital Humanities als f{\"a}cher{\"u}bergreifendes Forschungsparadigma. Konferenzabstracts}}, isbn = {{978-3-941379-05-3}}, pages = {{378--381}}, publisher = {{Universit{\"a}t Leipzig}}, title = {{{Wie verhalten sich Aktion{\"a}re bei Unternehmenszusammenschl{\"u}ssen? Modellierung sprachlicher Muster zur Analyse treibender Faktoren bei der Berichterstattung}}}, year = {{2016}}, } @misc{197, author = {{Dollmann, Markus}}, publisher = {{Universität Paderborn}}, title = {{{Frag die Anwender: Extraktion und Klassifikation von funktionalen Softwareanforderungen aus User-Generated-Content}}}, year = {{2016}}, } @inproceedings{1151, abstract = {{Welche Informationen über Unternehmenszusammenschlüsse werden in Zeitungsnachrichten vermittelt, und wie können diese Informationen automatisch extrahiert werden? Dies soll am Beispiel des Verhaltens von Aktionären während eines Zusammenschlusses ermittelt werden. Dazu werden die wichtigsten Aussagen über das Votum der Aktionäre im Hinblick auf eine automatische Erkennung sprachlich analysiert. Im Fokus stehen dabei die Berichte über Aktionärsabstimmungen hinsichtlich der Annahme bzw. Ablehnung eines Übernahmeangebots.}}, author = {{Stotz, Sophia and Geierhos, Michaela}}, booktitle = {{DHd 2016: Modellierung - Vernetzung - Visualisierung. Die Digital Humanities als fächerübergreifendes Forschungsparadigma. Konferenzabstracts, Universität Leipzig, 7. bis 12. März 2016}}, isbn = {{978-3-941379-05-3}}, location = {{Leipzig, Germany}}, pages = {{378--381}}, publisher = {{Nisaba-Verlag}}, title = {{{Wie verhalten sich Aktionäre bei Unternehmenszusammenschlüssen? Modellierung sprachlicher Muster zur Analyse treibender Faktoren bei der Berichterstattung}}}, year = {{2016}}, } @misc{1152, author = {{Geierhos, Michaela}}, booktitle = {{Enzyklopädie der Wirtschaftsinformatik}}, editor = {{Gronau, Norbert and Becker, Jörg and Sinz, Elmar and Suhl, Leena and Leimeister, Jan M.}}, keywords = {{Webmonitoring}}, publisher = {{GITO-Verlag}}, title = {{{Webmonitoring}}}, year = {{2016}}, }