Hasso-Plattner-Institut
Prof. Dr. Felix Naumann
 

Dr. Tim Repke

Former Ph.D. student at the Infomation Systems Research Group

Contact Information

August-Bebel-Straße 88
D-14482 Potsdam


Room: F-2.07
Phone: 0331 5509 - 1382
Email: Tim Repke
Public-Key: CFDF1C9A
Web: https://repke.eu


Research Interests

  • Text Mining
  • Data Visualisation
  • Web Information Extraction
  • Network Analysis
  • Privacy

Business Communication Analysis

Today's business communication is almost unimaginable without emails. They document discussions and decisions or summarise face-to-face meetings in the form of unstructured text or attachments and thus hold a significant amount of information about a business.
In very exceptional cases, for example when investigating a known case of fraud, specialists examine inboxes and attached files of involved personnel to determine the extent of the situation. However, the sheer quantity of data is unmanageable without some guidance by an exploration tool.
This work touches the fields of text mining, text summarisation, document classification, topic modelling, named entity extraction, entity linking, relationship extraction, as well as social network-, and graph analysis. In this project, we bring these disciplines together in a novel tool that helps steer forensic data exploration.

To find out more about the project, click here.

Supervision of Theses

  • Finding correleations between text, company networks, and stock prices over time
    (Kellermeier, April 2019, published at MIDAS@ECML/PKDD)
  • Evaluation of diachronic and multi-sense embeddings on sustainability research papers
    (Fischer, January 2020)
  • What do these two books have in common? – Multi-Aspect Embeddings for Fiction Novels
    (Kohlmeyer, May 2021)
  • Deep Learning for Rap Lyrics Generation Conditioned on Rhythm and Flow
    (Danz, June 2021)
  • Modeling the Evolution of Language Using Word Co-occurrences
    (Schwanhold, October 2021)

Teaching

Publications

  • Lasse Kohlmeyer, Tim Repke, Ralf Krestel: Novel Views on Novels: Embedding Multiple Facets of Long Texts. Proceedings of the International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT), 2021 (to appear)
    [Paper] 
  • Tim Repke, Ralf Krestel: Interactive Curation of Semantic Representations in Digital Libraries. Proceedings of the International Conference on Asia-Pacific Digital Libraries (ICADL), 2021 (to appear)
    [Paper] 
  • Tim Repke, Ralf Krestel: Extraction and Representation of Financial Entities from Text. Data Science for Economics and Finance. Springer, 2021
    [Chapter]  [Springer] 
  • Robert Schwanhold, Tim Repke, Ralf Krestel: Modeling the Evolution of Word Senses with Force-Directed Layouts of Co-occurrence Networks. Proceedings of the International Workshop on Computational Approaches to Historical Language Change (LChange@ACL), 2021
    [Paper]  [Project] 
  • Julian Risch, Tim Repke, Lasse Kohlmeyer, Ralf Krestel: ComEx: Comment Exploration on Online News Platforms. Joint Proceedings of the ACM IUI Workshops co-located with the ACM Conference on Intelligent User Interfaces (IUI), 2021
    [Paper]  [GitHub]  [Project]  [CEUR-WS] 
  • Tim Repke, Ralf Krestel: Robust Visualisation of Dynamic Text Collections: Measuring and Comparing Dimensionality Reduction Algorithms. Proceedings of the Conference on Human Information Interaction and Retrieval (CHIIR), 2021
    [Paper] 
  • Nicolas Alder, Tobias Bleifuß, Leon Bornemann, Felix Naumann, Tim Repke: Ein Data Engineering Kurs für 10.000 Teilnehmer. Datenbank-Spektrum 20:(1), 2021
    [Article]  [Springer]  [openHPI] 
  • Jan Ehmüller, Lasse Kohlmeyer, Holly McKee, Daniel Paeschke, Tim Repke, Ralf Krestel, Felix Naumann: Sense Tree: Discovery of New Word Senses with Graph-based Scoring. Lernen, Wissen, Daten, Analysen (LWDA), 2020
    [Paper]  [CEUR-WS]  [Project] 
  • Tim Repke, Ralf Krestel: Visualising Large Document Collections by Jointly Modeling Text and Network Structure. Proceedings of the Joint Conference on Digital Libraries (JCDL), 2020
    [Paper]  [Project] 
  • Tim Repke, Ralf Krestel: Exploration Interface for Jointly Visualised Text and Graph Data. Proceedings of the International Conference on Intelligent User Interfaces Companion (IUI), 2020
    [Paper]  [Project] 
  • Thomas Kellermeier, Tim Repke, Ralf Krestel: Mining Business Relationships from Stocks and News. Proceedings of the Workshop on Mining Data for Financial Applications (MIDAS@ECML-PKDD), 2019
    [Paper] 
  • Michael Loster, Tim Repke, Ralf Krestel, Felix Naumann, Jan Ehmueller, Benjamin Feldmann, Oliver Maspfuhl: The Challenges of Creating, Maintaining and Exploring Graphs of Financial Entities. Proceedings of the Fourth International Workshop on Data Science for Macro-Modeling (DSMM), 2018
    [Paper] 
  • Tim Repke, Ralf Krestel, Jakob Edding, Moritz Hartmann, Jonas Hering, Dennis Kipping, Hendrik Schmidt, Nico Scordialo, Alexander Zenner: Beacon in the Dark: A System for Interactive Exploration of Large Email Corpora. Proceedings of the International Conference on Information and Knowledge Management (CIKM), 2018
    [Paper v1]  [Paper v2]  [Project] 
  • Tim Repke, Ralf Krestel: Topic-aware Network Visualisation to Explore Large Email Corpora. International Workshop on Big Data Visual Exploration and Analytics (BigVis), 2018
    [Paper]  [Project] 
  • Tim Repke, Ralf Krestel: Bringing Back Structure to Free Text Email Conversations with Recurrent Neural Networks. Proceedings of the European Conference on Information Retrieval (ECIR), 2018
    [Paper]  [Project] 
  • M. Jürgen Giesler, Bettina Keller, Tim Repke, Rainer Leonhart, Joachim Weis, Rebecca Muckelbauer, Nina Rieckmann, Jacqueline Müller-Nordhorn, Gabriele Lucius-Hoene, Christine Holmberg: Effect of a Website That Presents Patients' Experiences on Self-Efficacy and Patient Competence of Colorectal Cancer Patients: Web-Based Randomized Controlled Trial. Journal of Medical Internet Research (JMIR) 19:(10), 2017
    [JMIR] 
  • Tim Repke, Michael Loster, Ralf Krestel: Comparing Features for Ranking Relationships Between Financial Entities Based on Text. Proceedings of the International Workshop on Data Science for Macro-Modeling with Financial and Economic Datasets (DSMM), 2017
    [Paper]  [Poster]  [Slides] 
  • Tim Repke: Extraction Of Citation Data From Websites Based On Visual Cues. , 2016
    [Thesis] 
  • Jennifer Engler, Sandra Adami, Yvonne Adam, Bettina Keller, Tim Repke, Hella Fügemann, Gabriele Lucius-Hoene, Jacqueline Müller-Nordhorn, Christine Holmberg: Using others’ experiences. Cancer patients’ expectations and navigation of a website providing narratives on prostate, breast and colorectal cancer. Patient Education and Counseling 99:(8), 2016
    [ScienceDirect]