@article{smith-etal-2017-evaluating,
    title = "Evaluating Visual Representations for Topic Understanding and Their Effects on Manually Generated Topic Labels",
    author = "Smith, Alison  and
      Lee, Tak Yeon  and
      Poursabzi-Sangdeh, Forough  and
      Boyd-Graber, Jordan  and
      Elmqvist, Niklas  and
      Findlater, Leah",
    editor = "Lee, Lillian  and
      Johnson, Mark  and
      Toutanova, Kristina",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "5",
    year = "2017",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://aclanthology.org/Q17-1001",
    doi = "10.1162/tacl_a_00042",
    pages = "1--16",
    abstract = "Probabilistic topic models are important tools for indexing, summarizing, and analyzing large document collections by their themes. However, promoting end-user understanding of topics remains an open research problem. We compare labels generated by users given four topic visualization techniques{---}word lists, word lists with bars, word clouds, and network graphs{---}against each other and against automatically generated labels. Our basis of comparison is participant ratings of how well labels describe documents from the topic. Our study has two phases: a labeling phase where participants label visualized topics and a validation phase where different participants select which labels best describe the topics{'} documents. Although all visualizations produce similar quality labels, simple visualizations such as word lists allow participants to quickly understand topics, while complex visualizations take longer but expose multi-word expressions that simpler visualizations obscure. Automatic labels lag behind user-created labels, but our dataset of manually labeled topics highlights linguistic patterns (e.g., hypernyms, phrases) that can be used to improve automatic topic labeling algorithms.",
}