Text Mining

This section provides additional information (code, datasets, embeddings) about past scientific work in the context of Text Mining for repeatiblity purposes.

• CHIIR 2021 resource under review PatentMatch: A Dataset for Matching Patent Claims & Prior Art
• CHIIR 2021 demo under review ComEx: Comment Exploration on Online News Platforms
• ECIR 2021 demo under review Multifaceted Domain-Specific Document Embedding

• WI-IAT 2020 HyCoNN: Hybrid Cooperative Neural Networks for Personalized News Discussion Recommendation
• CIKM 2020 A Dataset of Journalists’ Interactions With Their Readership: When Should Article Authors Reply to Reader Comments?
• ICWSM 2020 Top Comment or Flop Comment? Predicting and Explaining User Engagement in Online News Discussions
• TRAC@LREC 2020 Bagging BERT Models for Robust Aggression Identification
• TRAC@LREC 2020 Offensive Language Detection Explained
• JLCL 2020 Explaining Offensive Language Detection
• JCDL 2020 Hierarchical Document Classification as a Sequence Generation Task
• GermEval@KONVENS 2019 Offensive Language Identification using a German BERT model
• Datenbankspektrum 2019 Measuring and Facilitating Data Repeatability in Web Science 
• TRAC@COLING 2018 Aggression Identification Using Deep Learning and Data Augmentation
• ICADL 2018 Book Recommendation Beyond the Usual Suspects: Embedding Book Plots Together with Place and Time Information
• ICDIM 2018, DTA Journal 2018   Learning Patent Speak: Investigating Domain-Specific Word Embeddings and Domain-specific word embeddings for patent classification (Word Embeddings, Patent Classification)
• NAACL 2018 Prediction for the Newsroom: Which Articles Will Get the Most Comments?
• JCDL 2018, TPDL 2017 My Approach = Your Apparatus? Entropy-Based Topic Modeling on Multiple Domain-Specific Text Collections and What Should I Cite? Cross-Collection Reference Recommendation of Patents and Papers (Cross-Collection Topic Modeling)