@misc{RischKrestel2018, author = {Risch, Julian and Krestel, Ralf}, title = {My Approach = Your Apparatus?}, series = {Libraries}, journal = {Libraries}, publisher = {Association for Computing Machinery}, address = {New York}, isbn = {978-1-4503-5178-2}, issn = {2575-7865}, doi = {10.1145/3197026.3197038}, pages = {283 -- 292}, year = {2018}, abstract = {Comparative text mining extends from genre analysis and political bias detection to the revelation of cultural and geographic differences, through to the search for prior art across patents and scientific papers. These applications use cross-collection topic modeling for the exploration, clustering, and comparison of large sets of documents, such as digital libraries. However, topic modeling on documents from different collections is challenging because of domain-specific vocabulary. We present a cross-collection topic model combined with automatic domain term extraction and phrase segmentation. This model distinguishes collection-specific and collection-independent words based on information entropy and reveals commonalities and differences of multiple text collections. We evaluate our model on patents, scientific papers, newspaper articles, forum posts, and Wikipedia articles. In comparison to state-of-the-art cross-collection topic modeling, our model achieves up to 13\% higher topic coherence, up to 4\% lower perplexity, and up to 31\% higher document classification accuracy. More importantly, our approach is the first topic model that ensures disjunct general and specific word distributions, resulting in clear-cut topic representations.}, language = {en} } @article{RischKrestel2019, author = {Risch, Julian and Krestel, Ralf}, title = {Domain-specific word embeddings for patent classification}, series = {Data Technologies and Applications}, volume = {53}, journal = {Data Technologies and Applications}, number = {1}, publisher = {Emerald Group Publishing Limited}, address = {Bingley}, issn = {2514-9288}, doi = {10.1108/DTA-01-2019-0002}, pages = {108 -- 122}, year = {2019}, abstract = {Purpose Patent offices and other stakeholders in the patent domain need to classify patent applications according to a standardized classification scheme. The purpose of this paper is to examine the novelty of an application it can then be compared to previously granted patents in the same class. Automatic classification would be highly beneficial, because of the large volume of patents and the domain-specific knowledge needed to accomplish this costly manual task. However, a challenge for the automation is patent-specific language use, such as special vocabulary and phrases. Design/methodology/approach To account for this language use, the authors present domain-specific pre-trained word embeddings for the patent domain. The authors train the model on a very large data set of more than 5m patents and evaluate it at the task of patent classification. To this end, the authors propose a deep learning approach based on gated recurrent units for automatic patent classification built on the trained word embeddings. Findings Experiments on a standardized evaluation data set show that the approach increases average precision for patent classification by 17 percent compared to state-of-the-art approaches. In this paper, the authors further investigate the model's strengths and weaknesses. An extensive error analysis reveals that the learned embeddings indeed mirror patent-specific language use. The imbalanced training data and underrepresented classes are the most difficult remaining challenge. Originality/value The proposed approach fulfills the need for domain-specific word embeddings for downstream tasks in the patent domain, such as patent classification or patent analysis.}, language = {en} } @article{RischKrestel2020, author = {Risch, Julian and Krestel, Ralf}, title = {Toxic comment detection in online discussions}, series = {Deep learning-based approaches for sentiment analysis}, journal = {Deep learning-based approaches for sentiment analysis}, editor = {Agarwal, Basant and Nayak, Richi and Mittal, Namita and Patnaik, Srikanta}, publisher = {Springer}, address = {Singapore}, isbn = {978-981-15-1216-2}, issn = {2524-7565}, doi = {10.1007/978-981-15-1216-2_4}, pages = {85 -- 109}, year = {2020}, abstract = {Comment sections of online news platforms are an essential space to express opinions and discuss political topics. In contrast to other online posts, news discussions are related to particular news articles, comments refer to each other, and individual conversations emerge. However, the misuse by spammers, haters, and trolls makes costly content moderation necessary. Sentiment analysis can not only support moderation but also help to understand the dynamics of online discussions. A subtask of content moderation is the identification of toxic comments. To this end, we describe the concept of toxicity and characterize its subclasses. Further, we present various deep learning approaches, including datasets and architectures, tailored to sentiment analysis in online discussions. One way to make these approaches more comprehensible and trustworthy is fine-grained instead of binary comment classification. On the downside, more classes require more training data. Therefore, we propose to augment training data by using transfer learning. We discuss real-world applications, such as semi-automated comment moderation and troll detection. Finally, we outline future challenges and current limitations in light of most recent research publications.}, language = {en} } @phdthesis{Risch2020, author = {Risch, Julian}, title = {Reader comment analysis on online news platforms}, doi = {10.25932/publishup-48922}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-489222}, school = {Universit{\"a}t Potsdam}, pages = {xi, 135}, year = {2020}, abstract = {Comment sections of online news platforms are an essential space to express opinions and discuss political topics. However, the misuse by spammers, haters, and trolls raises doubts about whether the benefits justify the costs of the time-consuming content moderation. As a consequence, many platforms limited or even shut down comment sections completely. In this thesis, we present deep learning approaches for comment classification, recommendation, and prediction to foster respectful and engaging online discussions. The main focus is on two kinds of comments: toxic comments, which make readers leave a discussion, and engaging comments, which make readers join a discussion. First, we discourage and remove toxic comments, e.g., insults or threats. To this end, we present a semi-automatic comment moderation process, which is based on fine-grained text classification models and supports moderators. Our experiments demonstrate that data augmentation, transfer learning, and ensemble learning allow training robust classifiers even on small datasets. To establish trust in the machine-learned models, we reveal which input features are decisive for their output with attribution-based explanation methods. Second, we encourage and highlight engaging comments, e.g., serious questions or factual statements. We automatically identify the most engaging comments, so that readers need not scroll through thousands of comments to find them. The model training process builds on upvotes and replies as a measure of reader engagement. We also identify comments that address the article authors or are otherwise relevant to them to support interactions between journalists and their readership. Taking into account the readers' interests, we further provide personalized recommendations of discussions that align with their favored topics or involve frequent co-commenters. Our models outperform multiple baselines and recent related work in experiments on comment datasets from different platforms.}, language = {en} } @article{KrestelChikkamathHeweletal.2021, author = {Krestel, Ralf and Chikkamath, Renukswamy and Hewel, Christoph and Risch, Julian}, title = {A survey on deep learning for patent analysis}, series = {World patent information}, volume = {65}, journal = {World patent information}, publisher = {Elsevier}, address = {Amsterdam}, issn = {0172-2190}, doi = {10.1016/j.wpi.2021.102035}, pages = {13}, year = {2021}, abstract = {Patent document collections are an immense source of knowledge for research and innovation communities worldwide. The rapid growth of the number of patent documents poses an enormous challenge for retrieving and analyzing information from this source in an effective manner. Based on deep learning methods for natural language processing, novel approaches have been developed in the field of patent analysis. The goal of these approaches is to reduce costs by automating tasks that previously only domain experts could solve. In this article, we provide a comprehensive survey of the application of deep learning for patent analysis. We summarize the state-of-the-art techniques and describe how they are applied to various tasks in the patent domain. In a detailed discussion, we categorize 40 papers based on the dataset, the representation, and the deep learning architecture that were used, as well as the patent analysis task that was targeted. With our survey, we aim to foster future research at the intersection of patent analysis and deep learning and we conclude by listing promising paths for future work.}, language = {en} } @book{AdrianoBleifussChengetal.2019, author = {Adriano, Christian and Bleifuß, Tobias and Cheng, Lung-Pan and Diba, Kiarash and Fricke, Andreas and Grapentin, Andreas and Jiang, Lan and Kovacs, Robert and Krejca, Martin Stefan and Mandal, Sankalita and Marwecki, Sebastian and Matthies, Christoph and Mattis, Toni and Niephaus, Fabio and Pirl, Lukas and Quinzan, Francesco and Ramson, Stefan and Rezaei, Mina and Risch, Julian and Rothenberger, Ralf and Roumen, Thijs and Stojanovic, Vladeta and Wolf, Johannes}, title = {Technical report}, number = {129}, editor = {Meinel, Christoph and Plattner, Hasso and D{\"o}llner, J{\"u}rgen Roland Friedrich and Weske, Mathias and Polze, Andreas and Hirschfeld, Robert and Naumann, Felix and Giese, Holger and Baudisch, Patrick and Friedrich, Tobias and B{\"o}ttinger, Erwin and Lippert, Christoph}, publisher = {Universit{\"a}tsverlag Potsdam}, address = {Potsdam}, isbn = {978-3-86956-465-4}, issn = {1613-5652}, doi = {10.25932/publishup-42753}, url = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-427535}, publisher = {Universit{\"a}t Potsdam}, pages = {vi, 267}, year = {2019}, abstract = {Design and Implementation of service-oriented architectures imposes a huge number of research questions from the fields of software engineering, system analysis and modeling, adaptability, and application integration. Component orientation and web services are two approaches for design and realization of complex web-based system. Both approaches allow for dynamic application adaptation as well as integration of enterprise application. Commonly used technologies, such as J2EE and .NET, form de facto standards for the realization of complex distributed systems. Evolution of component systems has lead to web services and service-based architectures. This has been manifested in a multitude of industry standards and initiatives such as XML, WSDL UDDI, SOAP, etc. All these achievements lead to a new and promising paradigm in IT systems engineering which proposes to design complex software solutions as collaboration of contractually defined software services. Service-Oriented Systems Engineering represents a symbiosis of best practices in object-orientation, component-based development, distributed computing, and business process management. It provides integration of business and IT concerns. The annual Ph.D. Retreat of the Research School provides each member the opportunity to present his/her current state of their research and to give an outline of a prospective Ph.D. thesis. Due to the interdisciplinary structure of the research school, this technical report covers a wide range of topics. These include but are not limited to: Human Computer Interaction and Computer Vision as Service; Service-oriented Geovisualization Systems; Algorithm Engineering for Service-oriented Systems; Modeling and Verification of Self-adaptive Service-oriented Systems; Tools and Methods for Software Engineering in Service-oriented Systems; Security Engineering of Service-based IT Systems; Service-oriented Information Systems; Evolutionary Transition of Enterprise Applications to Service Orientation; Operating System Abstractions for Service-oriented Computing; and Services Specification, Composition, and Enactment.}, language = {en} }