Medical dataset classification for Kurdish short text over social media

Ari M Saeed; Shnya R Hussein; Chro M Ali; Tarik A Rashid

doi:10.1016/j.dib.2022.108089

Medical dataset classification for Kurdish short text over social media

Data Brief. 2022 Mar 23:42:108089. doi: 10.1016/j.dib.2022.108089. eCollection 2022 Jun.

Authors

Ari M Saeed¹, Shnya R Hussein¹, Chro M Ali¹, Tarik A Rashid²

Affiliations

¹ Computer Science Department, University of Halabja, KRG, Halabja, Kurdistan, Iraq.
² Computer Science and Engineering Department, University of Kurdistan-Hawlêr, KRG, Erbil, Kurdistan, Iraq.

Abstract

The Facebook application is used as a resource for collecting the comments of this dataset, The dataset consists of 6756 comments to create a Medical Kurdish Dataset (MKD). The samples are comments of users, which are gathered from different posts of pages (Medical, News, Economy, Education, and Sport). Six steps as a preprocessing technique are performed on the raw dataset to clean and remove noise in the comments by replacing characters. The comments (short text) are labeled for positive class (medical comment) and negative class (non-medical comment) as text classification. The percentage ratio of the negative class is 55% while the positive class is 45%.

Keywords: Kurdish short text; Machine learning; Medical text classification; Text pre-processing.