@inproceedings{RezapourBoppFiedleretal.2020,
  author    = {Rezvaneh Rezapour and Jutta Bopp and Norman Fiedler and Diana Steffen and Andreas Witt and Jana Diesner},
  title     = {Beyond Citations: Corpus-based Methods for Detecting the Impact of Research Outcomes on Society},
  series = {Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC), May 11-16, 2020, Palais du Pharo, Marseille, France},
  editor    = {Nicoletta Calzolari and Fr{\´e}d{\´e}ric B{\´e}chet and Philippe Blache and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and H{\´e}l{\`e}ne Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis},
  publisher = {European Language Resources Association},
  address   = {Paris},
  isbn      = {979-10-95546-34-4},
  url       = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-98422},
  pages     = {6777 -- 6785},
  year      = {2020},
  abstract  = {This paper proposes, implements and evaluates a novel, corpus-based approach for identifying categories indicative of the impact of research via a deductive (top-down, from theory to data) and an inductive (bottom-up, from data to theory) approach. The resulting categorization schemes differ in substance. Research outcomes are typically assessed by using bibliometric methods, such as citation counts and patterns, or alternative metrics, such as references to research in the media. Shortcomings with these methods are their inability to identify impact of research beyond academia (bibliometrics) and considering text-based impact indicators beyond those that capture attention (altmetrics). We address these limitations by leveraging a mixed-methods approach for eliciting impact categories from experts, project personnel (deductive) and texts (inductive). Using these categories, we label a corpus of project reports per category schema, and apply supervised machine learning to infer these categories from project reports. The classification results show that we can predict deductively and inductively derived impact categories with 76.39\% and 78.81\% accuracy (F1-score), respectively. Our approach can complement solutions from bibliometrics and scientometrics for assessing the impact of research and studying the scope and types of advancements transferred from academia to society.},
  language  = {en}
}