@inproceedings{alamr-atwell-2020-weka,
    title = "{WEKA} in Forensic Authorship Analysis: A corpus-based approach of Saudi Authors",
    author = "AlAmr, Mashael  and
      Atwell, Eric",
    editor = "Bhattacharyya, Pushpak  and
      Sharma, Dipti Misra  and
      Sangal, Rajeev",
    booktitle = "Proceedings of the 17th International Conference on Natural Language Processing (ICON)",
    month = dec,
    year = "2020",
    address = "Indian Institute of Technology Patna, Patna, India",
    publisher = "NLP Association of India (NLPAI)",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2020.icon-main.34/",
    pages = "257--260",
    abstract = "This is a pilot study that aims to explore the potential of using WEKA in forensic authorship analysis. It is a corpus-based research using data from Twitter collected from thirteen authors from Riyadh, Saudi Arabia. It examines the performance of unbalanced and balanced data sets using different classifiers and parameters of word grams. The attributes are dialect-specific linguistic features categorized as word grams. The findings further support previous studies in computational authorship identification."
}