@inproceedings{goel-sharma-2019-usf,
    title = "{USF} at {S}em{E}val-2019 Task 6: Offensive Language Detection Using {LSTM} With Word Embeddings",
    author = "Goel, Bharti  and
      Sharma, Ravi",
    editor = "May, Jonathan  and
      Shutova, Ekaterina  and
      Herbelot, Aurelie  and
      Zhu, Xiaodan  and
      Apidianaki, Marianna  and
      Mohammad, Saif M.",
    booktitle = "Proceedings of the 13th International Workshop on Semantic Evaluation",
    month = jun,
    year = "2019",
    address = "Minneapolis, Minnesota, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/S19-2139/",
    doi = "10.18653/v1/S19-2139",
    pages = "796--800",
    abstract = "In this paper, we present a system description for the SemEval-2019 Task 6 submitted by our team. For the task, our system takes tweet as an input and determine if the tweet is offensive or non-offensive (Sub-task A). In case a tweet is offensive, our system identifies if a tweet is targeted (insult or threat) or non-targeted like swearing (Sub-task B). In targeted tweets, our system identifies the target as an individual or group (Sub-task C). We used data pre-processing techniques like splitting hashtags into words, removing special characters, stop-word removal, stemming, lemmatization, capitalization, and offensive word dictionary. Later, we used keras tokenizer and word embeddings for feature extraction. For classification, we used the LSTM (Long short-term memory) model of keras framework. Our accuracy scores for Sub-task A, B and C are \textit{0.8128}, \textit{0.8167} and \textit{0.3662} respectively. Our results indicate that fine-grained classification to identify offense target was difficult for the system. Lastly, in the future scope section, we will discuss the ways to improve system performance."
}