@article{10.1371/journal.pone.0151885,
    author = {Yıldırım, Ahmet AND Üsküdarlı, Suzan AND Özgür, Arzucan},
    journal = {PLOS ONE},
    publisher = {Public Library of Science},
    title = {Identifying Topics in Microblogs Using Wikipedia},
    year = {2016},
    month = {03},
    volume = {11},
    url = {https://doi.org/10.1371/journal.pone.0151885},
    pages = {1-20},
    abstract = {Twitter is an extremely high volume platform for user generated contributions regarding any topic. The wealth of content created at real-time in massive quantities calls for automated approaches to identify the topics of the contributions. Such topics can be utilized in numerous ways, such as public opinion mining, marketing, entertainment, and disaster management. Towards this end, approaches to relate single or partial posts to knowledge base items have been proposed. However, in microblogging systems like Twitter, topics emerge from the culmination of a large number of contributions. Therefore, identifying topics based on collections of posts, where individual posts contribute to some aspect of the greater topic is necessary. Models, such as Latent Dirichlet Allocation (LDA), propose algorithms for relating collections of posts to sets of keywords that represent underlying topics. In these approaches, figuring out what the specific topic(s) the keyword sets represent remains as a separate task. Another issue in topic detection is the scope, which is often limited to specific domain, such as health. This work proposes an approach for identifying domain-independent specific topics related to sets of posts. In this approach, individual posts are processed and then aggregated to identify key tokens, which are then mapped to specific topics. Wikipedia article titles are selected to represent topics, since they are up to date, user-generated, sophisticated articles that span topics of human interest. This paper describes the proposed approach, a prototype implementation, and a case study based on data gathered during the heavily contributed periods corresponding to the four US election debates in 2012. The manually evaluated results (0.96 precision) and other observations from the study are discussed in detail.},
    number = {3},
    doi = {10.1371/journal.pone.0151885},
dataset={https://figshare.com/articles/data_tar_gz/2068665}
}