@inproceedings{zielinski-mutschke-2017-mining,
    title = "Mining Social Science Publications for Survey Variables",
    author = "Zielinski, Andrea  and
      Mutschke, Peter",
    editor = {Hovy, Dirk  and
      Volkova, Svitlana  and
      Bamman, David  and
      Jurgens, David  and
      O{'}Connor, Brendan  and
      Tsur, Oren  and
      Do{\u{g}}ru{\"o}z, A. Seza},
    booktitle = "Proceedings of the Second Workshop on {NLP} and Computational Social Science",
    month = aug,
    year = "2017",
    address = "Vancouver, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/iwcs-25-ingestion/W17-2907/",
    doi = "10.18653/v1/W17-2907",
    pages = "47--52",
    abstract = "Research in Social Science is usually based on survey data where individual research questions relate to observable concepts (variables). However, due to a lack of standards for data citations a reliable identification of the variables used is often difficult. In this paper, we present a work-in-progress study that seeks to provide a solution to the variable detection task based on supervised machine learning algorithms, using a linguistic analysis pipeline to extract a rich feature set, including terminological concepts and similarity metric scores. Further, we present preliminary results on a small dataset that has been specifically designed for this task, yielding a significant increase in performance over the random baseline."
}