@phdthesis{44323, abstract = {{Reading between the lines has so far been reserved for humans. The present dissertation addresses this research gap using machine learning methods. Implicit 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 (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? The 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. As 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.}}, author = {{Kersting, Joschka}}, pages = {{208}}, publisher = {{Universität der Bundeswehr München }}, title = {{{Identifizierung quantifizierbarer Bewertungsinhalte und -kategorien mittels Text Mining}}}, year = {{2023}}, } @inbook{46205, abstract = {{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.}}, author = {{Kersting, Joschka and Geierhos, Michaela}}, booktitle = {{Data Management Technologies and Applications}}, editor = {{Cuzzocrea, Alfredo and Gusikhin, Oleg and Hammoudi, Slimane and Quix, Christoph}}, isbn = {{9783031378898}}, issn = {{1865-0929}}, pages = {{45--65}}, publisher = {{Springer Nature Switzerland}}, title = {{{Towards Comparable Ratings: Quantifying Evaluative Phrases in Physician Reviews}}}, doi = {{10.1007/978-3-031-37890-4_3}}, volume = {{1860}}, year = {{2023}}, } @inbook{32179, abstract = {{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.}}, author = {{Kersting, Joschka and Ahmed, Mobeen and Geierhos, Michaela}}, booktitle = {{HCI International 2022 Posters}}, editor = {{Stephanidis, Constantine and Antona, Margherita and Ntoa, Stavroula}}, isbn = {{9783031064166}}, issn = {{1865-0929}}, keywords = {{On-The-Fly Computing, Chatbot, Knowledge Base}}, location = {{Virtual}}, pages = {{419----426}}, publisher = {{Springer International Publishing}}, title = {{{Chatbot-Enhanced Requirements Resolution for Automated Service Compositions}}}, doi = {{10.1007/978-3-031-06417-3_56}}, volume = {{1580}}, year = {{2022}}, } @inbook{17905, abstract = {{This chapter concentrates on aspect-based sentiment analysis, a form of opinion mining where algorithms detect sentiments expressed about features of products, services, etc. We especially focus on novel approaches for aspect phrase extraction and classification trained on feature-rich datasets. Here, we present two new datasets, which we gathered from the linguistically rich domain of physician reviews, as other investigations have mainly concentrated on commercial reviews and social media reviews so far. To give readers a better understanding of the underlying datasets, we describe the annotation process and inter-annotator agreement in detail. In our research, we automatically assess implicit mentions or indications of specific aspects. To do this, we propose and utilize neural network models that perform the here-defined aspect phrase extraction and classification task, achieving F1-score values of about 80% and accuracy values of more than 90%. As we apply our models to a comparatively complex domain, we obtain promising results. }}, author = {{Kersting, Joschka and Geierhos, Michaela}}, booktitle = {{Natural Language Processing in Artificial Intelligence -- NLPinAI 2020}}, editor = {{Loukanova, Roussanka}}, pages = {{163----189 }}, publisher = {{Springer}}, title = {{{Towards Aspect Extraction and Classification for Opinion Mining with Deep Sequence Networks}}}, doi = {{10.1007/978-3-030-63787-3_6}}, volume = {{939}}, year = {{2021}}, } @inproceedings{22051, author = {{Kersting, Joschka and Geierhos, Michaela}}, booktitle = {{Proceedings of the 10th International Conference on Data Science, Technology and Applications (DATA 2021)}}, location = {{Online}}, pages = {{275----284}}, publisher = {{SCITEPRESS}}, title = {{{Well-being in Plastic Surgery: Deep Learning Reveals Patients' Evaluations}}}, year = {{2021}}, } @inbook{22052, abstract = {{In this study, we describe a text processing pipeline that transforms user-generated text into structured data. To do this, we train neural and transformer-based models for aspect-based sentiment analysis. As most research deals with explicit aspects from product or service data, we extract and classify implicit and explicit aspect phrases from German-language physician review texts. Patients often rate on the basis of perceived friendliness or competence. The vocabulary is difficult, the topic sensitive, and the data user-generated. The aspect phrases come with various wordings using insertions and are not noun-based, which makes the presented case equally relevant and reality-based. To find complex, indirect aspect phrases, up-to-date deep learning approaches must be combined with supervised training data. We describe three aspect phrase datasets, one of them new, as well as a newly annotated aspect polarity dataset. Alongside this, we build an algorithm to rate the aspect phrase importance. All in all, we train eight transformers on the new raw data domain, compare 54 neural aspect extraction models and, based on this, create eight aspect polarity models for our pipeline. These models are evaluated by using Precision, Recall, and F-Score measures. Finally, we evaluate our aspect phrase importance measure algorithm.}}, author = {{Kersting, Joschka and Geierhos, Michaela}}, booktitle = {{Natural Language Processing and Information Systems}}, editor = {{Kapetanios, Epaminondas and Horacek, Helmut and Métais, Elisabeth and Meziane, Farid}}, location = {{Saarbrücken, Germany}}, pages = {{231----242}}, publisher = {{Springer}}, title = {{{Human Language Comprehension in Aspect Phrase Extraction with Importance Weighting}}}, volume = {{12801}}, year = {{2021}}, } @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}}, } @inproceedings{15580, abstract = {{This paper deals with aspect phrase extraction and classification in sentiment analysis. We summarize current approaches and datasets from the domain of aspect-based sentiment analysis. This domain detects sentiments expressed for individual aspects in unstructured text data. So far, mainly commercial user reviews for products or services such as restaurants were investigated. We here present our dataset consisting of German physician reviews, a sensitive and linguistically complex field. Furthermore, we describe the annotation process of a dataset for supervised learning with neural networks. Moreover, we introduce our model for extracting and classifying aspect phrases in one step, which obtains an F1-score of 80%. By applying it to a more complex domain, our approach and results outperform previous approaches.}}, author = {{Kersting, Joschka and Geierhos, Michaela}}, booktitle = {{Proceedings of the 12th International Conference on Agents and Artificial Intelligence (ICAART 2020) -- Special Session on Natural Language Processing in Artificial Intelligence (NLPinAI 2020)}}, keywords = {{Deep Learning, Natural Language Processing, Aspect-based Sentiment Analysis}}, location = {{Valetta, Malta}}, pages = {{391----400}}, publisher = {{SCITEPRESS}}, title = {{{Aspect Phrase Extraction in Sentiment Analysis with Deep Learning}}}, year = {{2020}}, } @inproceedings{15582, abstract = {{When it comes to increased digitization in the health care domain, privacy is a relevant topic nowadays. This relates to patient data, electronic health records or physician reviews published online, for instance. There exist different approaches to the protection of individuals’ privacy, which focus on the anonymization and masking of personal information subsequent to their mining. In the medical domain in particular, measures to protect the privacy of patients are of high importance due to the amount of sensitive data that is involved (e.g. age, gender, illnesses, medication). While privacy breaches in structured data can be detected more easily, disclosure in written texts is more difficult to find automatically due to the unstructured nature of natural language. Therefore, we take a detailed look at existing research on areas related to privacy protection. Likewise, we review approaches to the automatic detection of privacy disclosure in different types of medical data. We provide a survey of several studies concerned with privacy breaches in the medical domain with a focus on Physician Review Websites (PRWs). Finally, we briefly develop implications and directions for further research.}}, author = {{Buff, Bianca and Kersting, Joschka and Geierhos, Michaela}}, booktitle = {{Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods (ICPRAM 2020)}}, keywords = {{Identity Disclosure, Privacy Protection, Physician Review Website, De-Anonymization, Medical Domain}}, location = {{Valetta, Malta}}, pages = {{630----637}}, publisher = {{SCITEPRESS}}, title = {{{Detection of Privacy Disclosure in the Medical Domain: A Survey}}}, year = {{2020}}, } @inproceedings{15635, author = {{Kersting, Joschka and Geierhos, Michaela}}, booktitle = {{Proceedings of the 33rd International Florida Artificial Intelligence Research Symposium (FLAIRS) Conference}}, location = {{North Miami Beach, FL, USA}}, pages = {{282----285}}, publisher = {{AAAI}}, title = {{{Neural Learning for Aspect Phrase Extraction and Classification in Sentiment Analysis}}}, year = {{2020}}, } @inproceedings{15256, abstract = {{This paper deals with online customer reviews of local multi-service providers. While many studies investigate product reviews and online labour markets with service providers delivering intangible products “over the wire”, we focus on websites where providers offer multiple distinct services that can be booked, paid and reviewed online but are performed locally offline. This type of service providers has so far been neglected in the literature. This paper analyses reviews and applies sentiment analysis. It aims to gain new insights into local multi-service providers’ performance. There is a broad literature range presented with regard to the topics addressed. The results show, among other things, that providers with good ratings continue to perform well over time. We find that many positive reviews seem to encourage sales. On average, quantitative star ratings and qualitative ratings in the form of review texts match. Further results are also achieved in this study.}}, author = {{Kersting, Joschka and Geierhos, Michaela}}, booktitle = {{Proceedings of the 9th International Conference on Pattern Recognition Applications and Methods}}, keywords = {{Customer Reviews, Sentiment Analysis, Online Labour Markets}}, location = {{Valetta, Malta}}, pages = {{263----272}}, publisher = {{SCITEPRESS}}, title = {{{What Reviews in Local Online Labour Markets Reveal about the Performance of Multi-Service Providers}}}, 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{8529, author = {{Seemann, Nina and Merten, Marie-Luis}}, 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 = {{352--353}}, publisher = {{Zenodo}}, title = {{{UPB-Annotate: Ein maßgeschneidertes Toolkit für historische Texte}}}, doi = {{10.5281/ZENODO.2596094}}, 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}}, } @misc{13435, author = {{Friesen, Edwin}}, publisher = {{Universität Paderborn}}, title = {{{Requirements Engineering im OTF-Computing: Informationsextraktion und Unvollständigkeitskompensation mittels domänenspezifischer Wissensbasis}}}, 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}}, }