Julian Risch

I am a Ph.D. student at the Information Systems Group and a member of the HPI Research School. My research focuses on topic modeling and deep learning with applications in the field of comment analysis.

Contact Information

Prof.-Dr.-Helmert-Straße 2-3
D-14482 Potsdam
Room: F-2.08

Phone: +49 331 5509 272

Email: Julian Risch

Open Master's Theses

I provide supervision for an open Master's thesis on Natural Language Processing for Information Retrieval, which is described here. Further, feel free to discuss Master's thesis topics in the area of News Comment Analysis, such as Toxic Comment Classification, with me.

Teaching

Text Mining in Practice
Information Retrieval and Web Search
Recommender Systems
How Do Search Engines Work?
Text Mining
Hate Speech Detection (Master's Project Advisor)
Quality Management for Online News Comments (Master's Thesis Advisor)

Publications

Risch, J., Krestel, R.: Domain-specific word embeddings for patent classification. Data Technologies and Applications. (2019).

[ BibTeX ] [ Download ] [ Details ]

@article{risch2019domainspecific, abstract = {Patent offices and other stakeholders in the patent domain need to classify patent applications according to a standardized classification scheme. 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. To account for this language use, we present domain-specific pre-trained word embeddings for the patent domain. We train our model on a very large dataset of more than 5 million patents and evaluate it at the task of patent classification. To this end, we propose a deep learning approach based on gated recurrent units for automatic patent classification built on the trained word embeddings. Experiments on a standardized evaluation dataset show that our approach increases average precision for patent classification by 17 percent compared to state-of-the-art approaches. In this paper, we 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.}, author = {Risch, Julian and Krestel, Ralf}, journal = {Data Technologies and Applications}, keywords = {hpi myown web_science}, title = {Domain-specific word embeddings for patent classification}, year = 2019 }
Risch, J., Garda, S., Krestel, R.: Book Recommendation Beyond the Usual Suspects: Embedding Book Plots Together with Place and Time Information. Proceedings of the 20th International Conference On Asia-Pacific Digital Libraries (ICADL). bll. 227-239 (2018).

[ BibTeX ] [ Download ] [ Details ]

@inproceedings{noauthororeditor2018recommendation, abstract = {Content-based recommendation of books and other media is usually based on semantic similarity measures. While metadata can be compared easily, measuring the semantic similarity of narrative literature is challenging. Keyword-based approaches are biased to retrieve books of the same series or do not retrieve any results at all in sparser libraries. We propose to represent plots with dense vectors to foster semantic search for similar plots even if they do not have any words in common. Further, we propose to embed plots, places, and times in the same embedding space. Thereby, we allow arithmetics on these aspects. For example, a book with a similar plot but set in a different, user-specified place can be retrieved. We evaluate our findings on a set of 16,000 book synopses that spans literature from 500 years and 200 genres and compare our approach to a keyword-based baseline.}, author = {Risch, Julian and Garda, Samuele and Krestel, Ralf}, booktitle = {Proceedings of the 20th International Conference On Asia-Pacific Digital Libraries (ICADL)}, keywords = {hpi myown web_science}, month = {November}, pages = {227-239}, title = {Book Recommendation Beyond the Usual Suspects: Embedding Book Plots Together with Place and Time Information}, year = 2018 }
Risch, J., Krebs, E., Löser, A., Riese, A., Krestel, R.: Fine-Grained Classification of Offensive Language. Proceedings of GermEval (co-located with KONVENS). bll. 38-44 (2018).

[ BibTeX ] [ Download ] [ Details ]

@inproceedings{risch2018finegrained, abstract = {Social media platforms receive massive amounts of user-generated content that may include offensive text messages. In the context of the GermEval task 2018, we propose an approach for fine-grained classification of offensive language. Our approach comprises a Naive Bayes classifier, a neural network, and a rule-based approach that categorize tweets. In addition, we combine the approaches in an ensemble to overcome weaknesses of the single models. We cross-validate our approaches with regard to macro-average F1-score on the provided training dataset.}, author = {Risch, Julian and Krebs, Eva and Löser, Alexander and Riese, Alexander and Krestel, Ralf}, booktitle = {Proceedings of GermEval (co-located with KONVENS)}, keywords = {myown comments_analysis web_science isg}, month = {September}, pages = {38-44}, title = {Fine-Grained Classification of Offensive Language}, year = 2018 }
Risch, J., Krestel, R.: Learning Patent Speak: Investigating Domain-Specific Word Embeddings. Proceedings of the Thirteenth International Conference on Digital Information Management (ICDIM) (2018).

[ BibTeX ] [ Download ] [ Details ]

@inproceedings{risch2018learning, abstract = {A patent examiner needs domain-specific knowledge to classify a patent application according to its field of invention. Standardized classification schemes help to compare a patent application to previously granted patents and thereby check its novelty. Due to the large volume of patents, automatic patent classification would be highly beneficial to patent offices and other stakeholders in the patent domain. However, a challenge for the automation of this costly manual task is the patent-specific language use. To facilitate this task, we present domain-specific pre-trained word embeddings for the patent domain. We trained our model on a very large dataset of more than 5 million patents to learn the language use in this domain. We evaluated the quality of the resulting embeddings in the context of patent classification. To this end, we propose a deep learning approach based on gated recurrent units for automatic patent classification built on the trained word embeddings. Experiments on a standardized evaluation dataset show that our approach increases average precision for patent classification by 17 percent compared to state-of-the-art approaches.}, author = {Risch, Julian and Krestel, Ralf}, booktitle = {Proceedings of the Thirteenth International Conference on Digital Information Management (ICDIM)}, keywords = {myown web_science deep_learning isg}, month = {September}, title = {Learning Patent Speak: Investigating Domain-Specific Word Embeddings}, year = 2018 }
van Aken, B., Risch, J., Krestel, R., Löser, A.: Challenges for Toxic Comment Classification: An In-Depth Error Analysis. Proceedings of the 2nd Workshop on Abusive Language Online (co-located with EMNLP). bll. 33-42 (2018).

[ BibTeX ] [ Download ] [ Details ]

@inproceedings{vanaken2018challenges, abstract = {Toxic comment classification has become an active research field with many recently proposed approaches. However, while these approaches address some of the task’s challenges others still remain unsolved and directions for further research are needed. To this end, we compare different approaches on a new, large comment dataset and propose an ensemble that outperforms all individual models. Further, we validate our findings on a second dataset. The results of the ensemble enable us to perform an extensive error analysis, which reveals open challenges for state-of- the-art methods and directions towards pending future research. These challenges include missing paradigmatic context and inconsistent dataset labels.}, author = {van Aken, Betty and Risch, Julian and Krestel, Ralf and Löser, Alexander}, booktitle = {Proceedings of the 2nd Workshop on Abusive Language Online (co-located with EMNLP)}, keywords = {myown comments_analysis web_science isg}, month = {October}, pages = {33-42}, title = {Challenges for Toxic Comment Classification: An In-Depth Error Analysis}, year = 2018 }
Risch, J., Krestel, R.: Aggression Identification Using Deep Learning and Data Augmentation. Proceedings of the First Workshop on Trolling, Aggression and Cyberbullying (co-located with COLING). bll. 150-158 (2018).

[ BibTeX ] [ Download ] [ Details ]

@inproceedings{risch2018aggression, abstract = {Social media platforms allow users to share and discuss their opinions online. However, a minority of user posts is aggressive, thereby hinders respectful discussion, and — at an extreme level — is liable to prosecution. The automatic identification of such harmful posts is important, because it can support the costly manual moderation of online discussions. Further, the automation allows unprecedented analyses of discussion datasets that contain millions of posts. This system description paper presents our submission to the First Shared Task on Aggression Identification. We propose to augment the provided dataset to increase the number of labeled comments from 15,000 to 60,000. Thereby, we introduce linguistic variety into the dataset. As a consequence of the larger amount of training data, we are able to train a special deep neural net, which generalizes especially well to unseen data. To further boost the performance, we combine this neural net with three logistic regression classifiers trained on character and word n-grams, and hand-picked syntactic features. This ensemble is more robust than the individual single models. Our team named “Julian” achieves an F1-score of 60% on both English datasets, 63% on the Hindi Facebook dataset, and 38% on the Hindi Twitter dataset.}, author = {Risch, Julian and Krestel, Ralf}, booktitle = {Proceedings of the First Workshop on Trolling, Aggression and Cyberbullying (co-located with COLING)}, keywords = {hpi comments_analysis web_science isg}, month = {August}, pages = {150-158}, title = {Aggression Identification Using Deep Learning and Data Augmentation}, year = 2018 }
Risch, J., Krestel, R.: Delete or not Delete? Semi-Automatic Comment Moderation for the Newsroom. Proceedings of the First Workshop on Trolling, Aggression and Cyberbullying (co-located with COLING). bll. 166-176 (2018).

[ BibTeX ] [ Download ] [ Details ]

@inproceedings{risch2018delete, abstract = {Comment sections of online news providers have enabled millions to share and discuss their opinions on news topics. Today, moderators ensure respectful and informative discussions by deleting not only insults, defamation, and hate speech, but also unverifiable facts. This process has to be transparent and comprehensive in order to keep the community engaged. Further, news providers have to make sure to not give the impression of censorship or dissemination of fake news. Yet manual moderation is very expensive and becomes more and more unfeasible with the increasing amount of comments. Hence, we propose a semi-automatic, holistic approach, which includes comment features but also their context, such as information about users and articles. For evaluation, we present experiments on a novel corpus of 3 million news comments annotated by a team of professional moderators.}, author = {Risch, Julian and Krestel, Ralf}, booktitle = {Proceedings of the First Workshop on Trolling, Aggression and Cyberbullying (co-located with COLING)}, keywords = {hpi comments_analysis web_science isg}, month = {August}, pages = {166-176}, title = {Delete or not Delete? Semi-Automatic Comment Moderation for the Newsroom}, year = 2018 }
Ambroselli, C., Risch, J., Krestel, R., Loos, A.: Prediction for the Newsroom: Which Articles Will Get the Most Comments? Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL). bll. 193-199. ACL, New Orleans, Louisiana, USA (2018).

[ BibTeX ] [ Download ] [ Details ]

@inproceedings{krestel-naacl18, abstract = {The overwhelming success of the Web and mobile technologies has enabled millions to share their opinions publicly at any time. But the same success also endangers this freedom of speech due to closing down of participatory sites misused by individuals or interest groups. We propose to support manual moderation by proactively drawing the attention of our moderators to article discussions that most likely need their intervention. To this end, we predict which articles will receive a high number of comments. In contrast to existing work, we enrich the article with metadata, extract semantic and linguistic features, and exploit annotated data from a foreign language corpus. Our logistic regression model improves F1-scores by over 80% in comparison to state-of-the-art approaches.}, author = {Ambroselli, Carl and Risch, Julian and Krestel, Ralf and Loos, Andreas}, booktitle = {Proceedings of the 16th Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)}, keywords = {hpi comments_analysis web_science isg}, month = {June 1--6}, pages = {193-199}, publisher = {ACL}, title = {Prediction for the Newsroom: Which Articles Will Get the Most Comments?}, year = 2018 }
Risch, J., Krestel, R.: My Approach = Your Apparatus? Entropy-Based Topic Modeling on Multiple Domain-Specific Text Collections. Proceedings of the 18th ACM/IEEE Joint Conference on Digital Libraries (JCDL). bll. 283-292 (2018).

[ BibTeX ] [ Download ] [ Details ]

@inproceedings{risch2018approach, 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.}, author = {Risch, Julian and Krestel, Ralf}, booktitle = {Proceedings of the 18th ACM/IEEE Joint Conference on Digital Libraries (JCDL)}, keywords = {hpi topic_models web_science isg}, pages = {283-292}, title = {My Approach = Your Apparatus? Entropy-Based Topic Modeling on Multiple Domain-Specific Text Collections}, year = 2018 }
Maschler, F., Niephaus, F., Risch, J.: Real or Fake? Large-Scale Validation of Identity Leaks. 47. Jahrestagung der Gesellschaft für Informatik (INFORMATIK). bll. 2437-2448 (2017).

[ BibTeX ] [ Download ] [ Details ]

@inproceedings{maschler2017largescale, abstract = {On the Internet, criminal hackers frequently leak identity data on a massive scale. Subsequent criminal activities, such as identity theft and misuse, put Internet users at risk. Leak checker services enable users to check whether their personal data has been made public. However, automatic crawling and identification of leak data is error-prone for different reasons. Based on a dataset of more than 180 million leaked identity records, we propose a software system that identifies and validates identity leaks to improve leak checker services. Furthermore, we present a proficient assessment of leak data quality and typical characteristics that distinguish valid and invalid leaks.}, author = {Maschler, Fabian and Niephaus, Fabio and Risch, Julian}, booktitle = {47. Jahrestagung der Gesellschaft für Informatik (INFORMATIK)}, keywords = {hpi}, pages = {2437-2448}, title = {Real or Fake? Large-Scale Validation of Identity Leaks}, year = 2017 }
Krestel, R., Risch, J.: How Do Search Engines Work? A Massive Open Online Course with 4000 Participants. Proceedings of the Conference Lernen, Wissen, Daten, Analysen. bll. 259-271 (2017).

[ BibTeX ] [ Download ] [ Details ]

@inproceedings{krestel2017search, abstract = {Massive Open Online Courses (MOOCs) have introduced a new form of education. With thousands of participants per course, lectur- ers are confronted with new challenges in the teaching process. In this pa- per, we describe how we conducted an introductory information retrieval course for participants from all ages and educational backgrounds. We analyze different course phases and compare our experiences with regular on-site information retrieval courses at university.}, author = {Krestel, Ralf and Risch, Julian}, booktitle = {Proceedings of the Conference Lernen, Wissen, Daten, Analysen}, keywords = {web_science social_media isg}, month = {September}, pages = {259-271}, title = {How Do Search Engines Work? A Massive Open Online Course with 4000 Participants}, year = 2017 }
Risch, J., Krestel, R.: What Should I Cite? Cross-Collection Reference Recommendation of Patents and Papers. Proceedings of the International Conference on Theory and Practice of Digital Libraries (TPDL). bll. 40-46 (2017).

[ BibTeX ] [ Download ] [ Details ]

@inproceedings{risch2017what, abstract = {Research results manifest in large corpora of patents and scientific papers. However, both corpora lack a consistent taxonomy and references across different document types are sparse. Therefore, and because of contrastive, domain-specific language, recommending similar papers for a given patent (or vice versa) is challenging. We propose a hybrid recommender system that leverages topic distributions and key terms to recommend related work despite these challenges. As a case study, we evaluate our approach on patents and papers of two fields: medical and computer science. We find that topic-based recommenders complement term-based recommenders for documents with collection-specific language and increase mean average precision by up to 23%. As a result of our work, publications from both corpora form a joint digital library, which connects academia and industry.}, author = {Risch, Julian and Krestel, Ralf}, booktitle = {Proceedings of the International Conference on Theory and Practice of Digital Libraries (TPDL)}, keywords = {topic_models web_science isg}, pages = {40-46}, title = {What Should I Cite? Cross-Collection Reference Recommendation of Patents and Papers}, year = 2017 }
Bleifuß, T., Bülow, S., Frohnhofen, J., Risch, J., Wiese, G., Kruse, S., Papenbrock, T., Naumann, F.: Approximate Discovery of Functional Dependencies for Large Datasets. Proceedings of the International Conference on Information and Knowledge Management (CIKM). bll. 1803-1812. ACM, New York, NY, USA (2016).

[ BibTeX ] [ Download ] [ Details ]

@inproceedings{bleifuss2016approximate, abstract = {Functional dependencies (FDs) are an important prerequisite for various data management tasks, such as schema normalization, query optimization, and data cleansing. However, automatic FD discovery entails an exponentially growing search and solution space, so that even today’s fastest FD discovery algorithms are limited to small datasets only, due to long runtimes and high memory consumptions. To overcome this situation, we propose an approximate discovery strategy that sacrifices possibly little result correctness in return for large performance improvements. In particular, we introduce AID-FD, an algorithm that approximately discovers FDs within runtimes up to orders of magnitude faster than state-of-the-art FD discovery algorithms. We evaluate and compare our performance results with a focus on scalability in runtime and memory, and with measures for completeness, correctness, and minimality.}, address = {New York, NY, USA}, author = {Bleifuß, Tobias and Bülow, Susanne and Frohnhofen, Johannes and Risch, Julian and Wiese, Georg and Kruse, Sebastian and Papenbrock, Thorsten and Naumann, Felix}, booktitle = {Proceedings of the International Conference on Information and Knowledge Management (CIKM)}, keywords = {approximate hpi profiling discovery isg functional_dependencies}, pages = {1803-1812}, publisher = {ACM}, series = {CIKM '16}, title = {Approximate Discovery of Functional Dependencies for Large Datasets}, year = 2016 }
Hennig, P., Berger, P., Dullweber, C., Finke, M., Maschler, F., Risch, J., Meinel, C.: Social Media Story Telling. Proceedings of the 8th IEEE International Conference on Social Computing and Networking (SocialCom2015). bll. 279-284. , Chengdu, China (2015).

[ BibTeX ] [ Download ] [ Details ]

@inproceedings{2015_Hennig_SocialCom, abstract = {The number of documents on the web increases rapidly and often there is an enormous information overlap between different sources covering the same topic. Since it is impractical to read through all posts regarding a subject, there is a need for summaries combining the most relevant facts. In this context combining information from different sources in form of stories is an important method to provide perspective, while presenting and enriching the existing content in an interesting, natural and narrative way. Today, stories are often not available or they have been elaborately written and selected by journalists. Thus, we present an automated approach to create stories from multiple input documents. Furthermore the developed framework implements strategies to visualize stories and link content to related sources of information, such as images, tweets and encyclopedia records ready to be explored by the reader. Our approach combines deriving a story line from a graph of interlinked sources with a story-centric multi-document summarization.}, address = {Chengdu, China}, author = {Hennig, Patrick and Berger, Philipp and Dullweber, Christian and Finke, Moritz and Maschler, Fabian and Risch, Julian and Meinel, Christoph}, booktitle = {Proceedings of the 8th IEEE International Conference on Social Computing and Networking (SocialCom2015)}, keywords = {hpi myown}, month = 12, pages = {279-284}, title = {Social Media Story Telling}, year = 2015 }
Schmidt, D., Frohnhofen, J., Knebel, S., Meinel, F., Perchyk, M., Risch, J., Striebel, J., Wachtel, J., Baudisch, P.: Ergonomic Interaction for Touch Floors. Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems. bll. 3879-3888. ACM, Seoul, Republic of Korea (2015).

[ BibTeX ] [ Download ] [ Details ]

@inproceedings{Schmidt:2015:EIT:2702123.2702254, abstract = {The main appeal of touch floors is that they are the only direct touch form factor that scales to arbitrary size, therefore allowing direct touch to scale to very large numbers of display objects. In this paper, however, we argue that the price for this benefit is bad physical ergonomics: prolonged standing, especially in combination with looking down, quickly causes fatigue and repetitive strain. We propose addressing this issue by allowing users to operate touch floors in any pose they like, including sitting and lying. To allow users to transition between poses seamlessly, we present a simple pose-aware view manager that supports users by adjusting the entire view to the new pose. We support the main assumption behind the work with a simple study that shows that several poses are indeed more ergonomic for touch floor interaction than standing. We ground the design of our view manager by analyzing, which screen regions users can see and touch in each of the respective poses.}, address = {New York, NY, USA}, author = {Schmidt, Dominik and Frohnhofen, Johannes and Knebel, Sven and Meinel, Florian and Perchyk, Mariya and Risch, Julian and Striebel, Jonathan and Wachtel, Julia and Baudisch, Patrick}, booktitle = {Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems}, keywords = {hpi}, pages = {3879-3888}, publisher = {ACM}, series = {CHI '15}, title = {Ergonomic Interaction for Touch Floors}, year = 2015 }