Vis4NLP2024

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/3607004

Browse

Browsing Vis4NLP2024 by Title

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Using the Word Rain Technique to Visualize Longitudinal Changes in Periodicals from the Swedish Diabetes Association
    (The Eurographics Association, 2024) Skeppstedt, Maria; Aangenendt, Gijs; Yousef, Tariq; Al-Khatib, Khalid
    The Word Rain visualization technique is a development of the classic word cloud that aims to retain the simplicity of the word cloud, while at the same time making it possible to use the text visualization for exploring and comparing corpora. We here showcase how the Word Rain technique can be used for visualizing longitudinal changes by displaying the most prominent words for each (user-defined) time period in the corpus. ''Most prominent'' for a time period can, however, have different meanings depending on how the word rain is configured. We here list a number of possible configuration types, and we also provide examples of word rains generated using some of these configurations. We showcase the configuration settings on a corpus of periodicals from the Swedish Diabetes Association.
  • Thumbnail Image
    Item
    Vis4NLP 2024: Frontmatter
    (The Eurographics Association, 2024) Yousef, Tariq; Al-Khatib, Khalid; Yousef, Tariq; Al-Khatib, Khalid
  • Thumbnail Image
    Item
    Visual Analysis of Humor Assessment Annotations for News Headlines in the Humicroedit Data Set
    (The Eurographics Association, 2024) Kucher, Kostiantyn; Akkurt, Elin; Folde, Johanna; Kerren, Andreas; Yousef, Tariq; Al-Khatib, Khalid
    Effective utilization of training data is a critical component for the success of any artificial intelligence algorithm, including natural language processing (NLP) tasks. One particular task of interest is related to detecting or ranking humor in texts, as exemplified by the Humicroedit data set used for the SemEval 2020 task of assessing humor in micro-edited news headlines. Rather than focusing on text classification or prediction, in this study, we focus on gaining a deeper understanding and utilization of the data through the use of information visualization techniques facilitated by the established NLP methods such as sentiment analysis and topic modeling. We describe the design of an interactive visualization tool prototype that relies on multiple coordinated views to allow the user explore and analyze the relationships between the annotated humor scores, sentiments, and topics. Evaluation of the proposed approach involves a case study with the Humicroedit data set as well as domain expert reviews with four participants. The experts deemed the prototype useful for its purpose and saw potential in exploring similar data sets with it, as well as further potential applications in their line of work. Our study thus contributes to the body of work on visual text analytics for supporting computational humor analysis as well as annotated text data analysis in general.