TY - CHAP AB - We present a concept for quantifying evaluative phrases to later compare rating texts numerically instead of just relying on stars or grades. We achievethis by combining deep learning models in an aspect-based sentiment analysis pipeline along with sentiment weighting, polarity, and correlation analyses that combine deep learning results with metadata. The results provide new insights for the medical field. Our application domain, physician reviews, shows that there are millions of review texts on the Internet that cannot yet be comprehensively analyzed because previous studies have focused on explicit aspects from other domains (e.g., products). We identify, extract, and classify implicit and explicit aspect phrases equally from German-language review texts. To do so, we annotated aspect phrases representing reviews on numerous aspects of a physician, medical practice, or practice staff. We apply the best performing transformer model, XLM-RoBERTa, to a large physician review dataset and correlate the results with existing metadata. As a result, we can show different correlations between the sentiment polarity of certain aspect classes (e.g., friendliness, practice equipment) and physicians’ professions (e.g., surgeon, ophthalmologist). As a result, we have individual numerical scores that contain a variety of information based on deep learning algorithms that extract textual (evaluative) information and metadata from the Web. AU - Kersting, Joschka AU - Geierhos, Michaela ED - Cuzzocrea, Alfredo ED - Gusikhin, Oleg ED - Hammoudi, Slimane ED - Quix, Christoph ID - 46205 SN - 1865-0929 T2 - Data Management Technologies and Applications TI - Towards Comparable Ratings: Quantifying Evaluative Phrases in Physician Reviews VL - 1860 ER - TY - CONF AU - Peters, Tobias Martin AU - Visser, Roel W. ID - 48595 SN - 1865-0929 T2 - Communications in Computer and Information Science TI - The Importance of Distrust in AI ER - TY - CHAP AB - This work addresses the automatic resolution of software requirements. In the vision of On-The-Fly Computing, software services should be composed on demand, based solely on natural language input from human users. To enable this, we build a chatbot solution that works with human-in-the-loop support to receive, analyze, correct, and complete their software requirements. The chatbot is equipped with a natural language processing pipeline and a large knowledge base, as well as sophisticated dialogue management skills to enhance the user experience. Previous solutions have focused on analyzing software requirements to point out errors such as vagueness, ambiguity, or incompleteness. Our work shows how apps can collaborate with users to efficiently produce correct requirements. We developed and compared three different chatbot apps that can work with built-in knowledge. We rely on ChatterBot, DialoGPT and Rasa for this purpose. While DialoGPT provides its own knowledge base, Rasa is the best system to combine the text mining and knowledge solutions at our disposal. The evaluation shows that users accept 73% of the suggested answers from Rasa, while they accept only 63% from DialoGPT or even 36% from ChatterBot. AU - Kersting, Joschka AU - Ahmed, Mobeen AU - Geierhos, Michaela ED - Stephanidis, Constantine ED - Antona, Margherita ED - Ntoa, Stavroula ID - 32179 KW - On-The-Fly Computing KW - Chatbot KW - Knowledge Base SN - 1865-0929 T2 - HCI International 2022 Posters TI - Chatbot-Enhanced Requirements Resolution for Automated Service Compositions VL - 1580 ER - TY - CHAP AB - Modern traffic control systems are key to cope with current and future traffic challenges. In this paper information obtained from a microscopic traffic estimation using various data sources is used to feed a new developed traffic control approach. The presented method can control a traffic area with multiple traffic light systems (TLS) reacting to individual road users and pedestrians. In contrast to widespread green time extension techniques, this control selects the best phase sequence by analyzing the current traffic state reconstructed in SUMO and its predicted progress. To achieve this, the key aspect of the control strategy is to use Model Predictive Control (MPC). In order to maintain realism for real world applications, among other things, the traffic phase transitions are modelled in detail and integrated within the prediction. For the efficiency, the approach incorporates a fuzzy logic preselection of all phases reducing the computational effort. The evaluation itself is able to be easily adjusted to focus on various objectives like low occupancies, reducing waiting times and emissions, few number of phase transitions etc. determining the best switching times for the selected phases. Exemplary traffic simulations demonstrate the functionality of the MPC-based control and, in addition, some aspects under development like the real-world communication network are also discussed. AU - Malena, Kevin AU - Link, Christopher AU - Bußemas, Leon AU - Gausemeier, Sandra AU - Trächtler, Ansgar ED - Klein, Cornel ED - Jarke, Mathias ED - Helfert, Markus ED - Berns, Karsten ED - Gusikhin, Oleg ID - 33849 KW - Traffic control KW - Traffic estimation KW - Real-time KW - MPC KW - Fuzzy KW - Isolated intersection KW - Networked intersection KW - Sensor fusion SN - 1865-0929 T2 - Communications in Computer and Information Science TI - Traffic Estimation and MPC-Based Traffic Light System Control in Realistic Real-Time Traffic Environments VL - 1612 ER - TY - CONF AU - Jovanovikj, Ivan AU - Weidmann, Nils AU - Yigitbas, Enes AU - Anjorin, Anthony AU - Sauer, Stefan AU - Engels, Gregor ED - Babur, Önder ED - Denil, Joachim ED - Vogel-Heuser, Birgit ID - 21483 SN - 1865-0929 T2 - Proceedings of the First International Conference on Systems Modelling and Management, ICSMM 2020 TI - A Model-Driven Mutation Framework for Validation of Test Case Migration ER - TY - CONF AU - Fockel, Markus AU - Merschjohann, Sven AU - Fazal-Baqaie, Masud AU - Förder, Torsten AU - Hausmann, Stefan AU - Waldeck, Boris ID - 22805 SN - 1865-0929 T2 - European System, Software & Service Process Improvement & Innovation Conference (EuroSPI 2019) TI - Designing and Integrating IEC 62443 Compliant Threat Analysis VL - 1060 ER - TY - CHAP AB - 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. AU - Bäumer, Frederik Simon AU - Kersting, Joschka AU - Kuršelis, Vytautas AU - Geierhos, Michaela ED - Damaševičius, Robertas ED - Vasiljevienė, Giedrė ID - 4338 KW - Lithuanian physician review websites KW - Medical service ratings SN - 1865-0929 T2 - Communications in Computer and Information Science TI - Rate Your Physician: Findings from a Lithuanian Physician Rating Website VL - 920 ER - TY - CONF AB - 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. AU - Bäumer, Frederik Simon AU - Geierhos, Michaela ED - Damaševičius, Robertas ED - Vasiljevienė, Giedrė ID - 4339 KW - Inaccuracy detection KW - Natural language software requirements SN - 1865-0929 T2 - Proceedings of the 24th International Conference on Information and Software Technologies (ICIST 2018) TI - NLP in OTF Computing: Current Approaches and Open Challenges VL - 920 ER - TY - CHAP AU - Hallmann, Corinna AU - Burmeister, Sascha Christian AU - Wissing, Michaela AU - Suhl, Leena ID - 14856 SN - 1865-0929 T2 - Communications in Computer and Information Science TI - Heuristics and Simulation for Water Tank Optimization ER - TY - CONF AU - Ghribi, Ines AU - Abdallah, Riadh Ben AU - Khalgui, Mohamed AU - Platzner, Marco ID - 14893 SN - 1865-0929 T2 - Communications in Computer and Information Science TI - I-Codesign: A Codesign Methodology for Reconfigurable Embedded Systems ER -