@article{53801,
  abstract     = {{In this study, we evaluate the impact of gender-biased data from German-language physician reviews on the fairness of fine-tuned language models. For two different downstream tasks, we use data reported to be gender biased and aggregate it with annotations. First, we propose a new approach to aspect-based sentiment analysis that allows identifying, extracting, and classifying implicit and explicit aspect phrases and their polarity within a single model. The second task we present is grade prediction, where we predict the overall grade of a review on the basis of the review text. For both tasks, we train numerous transformer models and evaluate their performance. The aggregation of sensitive attributes, such as a physician’s gender and migration background, with individual text reviews allows us to measure the performance of the models with respect to these sensitive groups. These group-wise performance measures act as extrinsic bias measures for our downstream tasks. In addition, we translate several gender-specific templates of the intrinsic bias metrics into the German language and evaluate our fine-tuned models. Based on this set of tasks, fine-tuned models, and intrinsic and extrinsic bias measures, we perform correlation analyses between intrinsic and extrinsic bias measures. In terms of sensitive groups and effect sizes, our bias measure results show different directions. Furthermore, correlations between measures of intrinsic and extrinsic bias can be observed in different directions. This leads us to conclude that gender-biased data does not inherently lead to biased models. Other variables, such as template dependency for intrinsic measures and label distribution in the data, must be taken into account as they strongly influence the metric results. Therefore, we suggest that metrics and templates should be chosen according to the given task and the biases to be assessed. }},
  author       = {{Kersting, Joschka and Maoro, Falk and Geierhos, Michaela}},
  issn         = {{0169-023X}},
  journal      = {{Data & Knowledge Engineering}},
  keywords     = {{Language model fairness, Aspect phrase classification, Grade prediction, Physician reviews}},
  publisher    = {{Elsevier}},
  title        = {{{Towards comparable ratings: Exploring bias in German physician reviews}}},
  doi          = {{10.1016/j.datak.2023.102235}},
  volume       = {{148}},
  year         = {{2023}},
}

@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}},
}

@article{4682,
  author       = {{Schmiedel, T. and Müller, Oliver and vom Brocke, J.}},
  journal      = {{Organizational Research Methods}},
  keywords     = {{online reviews, organizational culture, structural topic model, topic modeling, tutorial}},
  pages        = {{941----968 }},
  title        = {{{Topic Modeling as a Strategy of Inquiry in Organizational Research: A Tutorial With an Application Example on Organizational Culture}}},
  doi          = {{https://doi.org/10.1177/1094428118773858}},
  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{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}},
}

@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}},
}

@article{4691,
  abstract     = {{Analysts have estimated that more than 80 percent of today’s data is stored in unstructured form (e.g., text, audio, image, video)—much of it expressed in rich and ambiguous natural language. Traditionally, to analyze natural language, one has used qualitative data-analysis approaches, such as manual coding. Yet, the size of text data sets obtained from the Internet makes manual analysis virtually impossible. In this tutorial, we discuss the challenges encountered when applying automated text-mining techniques in information systems research. In particular, we showcase how to use probabilistic topic modeling via Latent Dirichlet allocation, an unsupervised text-mining technique, with a LASSO multinomial logistic regression to explain user satisfaction with an IT artifact by automatically analyzing more than 12,000 online customer reviews. For fellow information systems researchers, this tutorial provides guidance for conducting text-mining studies on their own and for evaluating the quality of others.}},
  author       = {{Debortoli, Stefan and Müller, Oliver and Junglas, Iris and vom Brocke, Jan}},
  isbn         = {{9781615679119}},
  issn         = {{1529-3181}},
  journal      = {{Communications of the Association for Information Systems}},
  keywords     = {{Latent dirichlet allocation, Online customer reviews, Text mining, Topic modeling, User satisfaction}},
  pages        = {{555--582}},
  title        = {{{Text Mining for Information Systems Researchers: An Annotated Tutorial}}},
  doi          = {{10.17705/1CAIS.03907}},
  year         = {{2016}},
}

@inbook{1149,
  abstract     = {{The contacts a health care provider (HCP), like a physician, has to other HCPs is perceived as a quality characteristic by patients. So far, only the German physician rating website jameda.de gives information about the interconnectedness of HCPs in business networks. However, this network has to be maintained manually and is thus incomplete. We therefore developed a system for uncovering latent connectivity of HCPs in online reviews to provide users with more valuable information about their HCPs. The overall goal of this approach is to extend already existing business networks of HCPs by integrating connections that are newly discovered by our system. Our most recent evaluation results are promising: 70.8 % of the connections extracted from the reviews texts were correctly identified and in total 3,788 relations were recognized that have not been displayed in jameda.de’s network before.}},
  author       = {{Bäumer, Frederik Simon and Geierhos, Michaela and Schulze, Sabine}},
  booktitle    = {{Information and Software Technologies. 21st International Conference, ICIST 2015, Druskininkai, Lithuania, October 15-16, 2015. Proceedings}},
  editor       = {{Dregvaite, Giedre and Damasevicius, Robertas}},
  isbn         = {{978-3-319-24769-4}},
  keywords     = {{Latent Connectivity, Person Named Entity Recognition and Disambiguation, Health Care Provider Reviews}},
  location     = {{Druskininkai, Lithuania}},
  pages        = {{3--15}},
  publisher    = {{Springer}},
  title        = {{{A System for Uncovering Latent Connectivity of Health Care Providers in Online Reviews}}},
  doi          = {{10.1007/978-3-319-24770-0_1}},
  volume       = {{538}},
  year         = {{2015}},
}

@inproceedings{8926,
  abstract     = {{Piezoelectric transformers are well known since the publication of some patent applications at the end of the 1950s. But until today their only business use lies in the field of backlighting systems for LCDs. Due to key features as light-weight, flatness, high step-up at low volume and high efficiency piezoelectric transformers should be usable in a much broader range of applications. This contribution returns to mind their operating principle, shows how to model and to develop such devices as well as give some aspects for development trends that will lead to further applications.}},
  author       = {{Hemsel, Tobias and Littmann, Walter and Wallaschek, Jörg}},
  booktitle    = {{Ultrasonics Symposium, 2002. Proceedings. 2002 IEEE}},
  issn         = {{1051-0117}},
  keywords     = {{piezoelectric devices, reviews, transformers, backlighting systems, flatness, high efficiency piezoelectric transformers, high step-up, light-weight, low volume, operating principle, piezoelectric transformers, Circuits, Costs, Electromagnetic devices, Electromagnetic fields, Mechanical energy, Piezoelectric materials, Power electronics, Switching frequency, Transformers, Vibrations}},
  number       = {{vol.1}},
  pages        = {{645--648}},
  title        = {{{Piezoelectric transformers - state of the art and development trends}}},
  doi          = {{10.1109/ULTSYM.2002.1193485}},
  volume       = {{1}},
  year         = {{2002}},
}