@article{2331, abstract = {{A user generally writes software requirements in ambiguous and incomplete form by using natural language; therefore, a software developer may have difficulty in clearly understanding what the meanings are. To solve this problem with automation, we propose a classifier for semantic annotation with manually pre-defined semantic categories. To improve our classifier, we carefully designed syntactic features extracted by constituency and dependency parsers. Even with a small dataset and a large number of classes, our proposed classifier records an accuracy of 0.75, which outperforms the previous model, REaCT.}}, author = {{Kim, Yeongsu and Lee, Seungwoo and Dollmann, Markus and Geierhos, Michaela}}, issn = {{2207-6360}}, journal = {{International Journal of Advanced Science and Technology}}, keywords = {{Software Engineering, Natural Language Processing, Semantic Annotation, Machine Learning, Feature Engineering, Syntactic Structure}}, pages = {{123--136}}, publisher = {{SERSC Australia}}, title = {{{Improving Classifiers for Semantic Annotation of Software Requirements with Elaborate Syntactic Structure}}}, doi = {{10.14257/ijast.2018.112.12}}, volume = {{112}}, year = {{2018}}, } @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{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}}, } @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}}, } @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{176, abstract = {{Users prefer natural language software requirements because of their usability and accessibility. When they describe their wishes for software development, they often provide off-topic information. We therefore present an automated approach for identifying and semantically annotating the on-topic parts of the given descriptions. It is designed to support requirement engineers in the requirement elicitation process on detecting and analyzing requirements in user-generated content. Since no lexical resources with domain-specific information about requirements are available, we created a corpus of requirements written in controlled language by instructed users and uncontrolled language by uninstructed users. We annotated these requirements regarding predicate-argument structures, conditions, priorities, motivations and semantic roles and used this information to train classifiers for information extraction purposes. The approach achieves an accuracy of 92% for the on- and off-topic classification task and an F1-measure of 72% for the semantic annotation.}}, author = {{Dollmann, Markus and Geierhos, Michaela}}, booktitle = {{Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP)}}, location = {{Austin, TX, USA}}, pages = {{1807--1816}}, publisher = {{Association for Computational Linguistics (ACL)}}, title = {{{On- and Off-Topic Classification and Semantic Annotation of User-Generated Software Requirements}}}, year = {{2016}}, } @inproceedings{25409, author = {{Baeumer, Frederik Simon and Dollmann, Markus and Geierhos, Michaela}}, issn = {{1877-0509}}, pages = {{417--424}}, publisher = {{Elsevier}}, title = {{{Find a Physician by Matching Medical Needs described in your Own Words}}}, volume = {{63}}, year = {{2015}}, } @inproceedings{1148, abstract = {{The individual search for information about physicians on Web 2.0 platforms can affect almost all aspects of our lives. People can directly access physician rating websites via web browsers or use any search engine to find physician reviews and ratings filtered by location resp. specialty. However, sometimes keyword search does not meet user needs because of the disagreement of users’ common terms queries for symptoms and the widespread medical terminology. In this paper, we present the prototype of a specialised search engine that overcomes this by indexing user-generated content (i.e., review texts) for physician discovery and provides automatic suggestions as well as an appropriate visualisation. On the one hand, we consider the available numeric physician ratings as sorting criterion for the ranking of query results. Furthermore, we extended existing ranking algorithms with respect to domain-specific types and physicians ratings on the other hand. We gathered more than 860,000 review texts and collected more than 213,000 physician records. A random test shows that about 19.7% of 5,100 different words in total are health- related and partly belong to consumer health vocabularies. Our evaluation results show that the query results fit user's particular health issues when seeking for physicians.}}, author = {{Bäumer, Frederik Simon and Dollmann, Markus and Geierhos, Michaela}}, booktitle = {{The 6th International Conference on Emerging Ubiquitous Systems and Pervasive Networks (EUSPN 2015) / The 5th International Conference on Current and Future Trends of Information and Communication Technologies in Healthcare (ICTH-2015) / Affiliated Workshops}}, editor = {{Shakshuki, Elhadi M.}}, issn = {{18770509}}, keywords = {{Physician Discovery, Consumer Health Vocabulary, Common Terms Query}}, location = {{Berlin, Germany}}, pages = {{417--424}}, publisher = {{Elsevier}}, title = {{{Find a Physician by Matching Medical Needs described in your Own Words}}}, doi = {{10.1016/j.procs.2015.08.362}}, volume = {{63}}, year = {{2015}}, } @inproceedings{1135, abstract = {{In this paper, we describe our system developed for the GErman SenTiment AnaLysis shared Task (GESTALT) for participation in the Maintask 2: Subjective Phrase and Aspect Extraction from Product Reviews. We present a tool, which identifies subjective and aspect phrases in German product reviews. For the recognition of subjective phrases, we pursue a lexicon-based approach. For the extraction of aspect phrases from the reviews, we consider two possible ways: Besides the subjectivity and aspect look-up, we also implemented a method to establish which subjective phrase belongs to which aspect. The system achieves better results for the recognition of aspect phrases than for the subjective identification.}}, author = {{Dollmann, Markus and Geierhos, Michaela}}, booktitle = {{Workshop Proceedings of the 12th Edition of the KONVENS Conference}}, editor = {{Faaß, Gertrud and Ruppenhofer, Josef}}, isbn = {{978-3-934105-47-8}}, keywords = {{corpus linguistics, sentiment analysis}}, location = {{Hildesheim, Germany}}, pages = {{185--191}}, publisher = {{Universitätsverlag Hildesheim}}, title = {{{SentiBA: Lexicon-based Sentiment Analysis on German Product Reviews}}}, year = {{2014}}, }