Explainable AI for sentiment analysis of human metapneumovirus (HMPV) using XLNet
Md Shahriar Hossain Apu, Md Saiful Islam, Tanjim Taharat Aurpa, Sharad Hasan · 2026
Read Explainable AI for sentiment analysis of human metapneumovirus (HMPV) using XLNet by Md Shahriar Hossain Apu, Md Saiful Islam, Tanjim Taharat Aurpa, Sharad Hasan (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0351265.txt.
Description
Md Shahriar Hossain Apu and three colleagues read the public mood about human metapneumovirus from social media, in PLOS ONE in 2026. The respiratory virus, usually mild but dangerous for the elderly and the immune compromised, drew anxious attention during its 2024 outbreak in China and beyond. The team applied sentiment analysis to YouTube discussion to map reactions running from fear to trust, arguing health agencies should know which they face before writing guidance.
Their classifier, built on the XLNet language model, sorted posts with accuracy above ninety-three percent. An explainability layer showed which words and phrases pushed each judgment, so the output can be audited rather than merely believed. The authors pitch the approach as an early listening post for outbreak communication: catch rising fear or carelessness early, answer misinformation precisely, and pitch preventive advice at the audience that actually exists.
Catalog record
| CREATOR | Md Shahriar Hossain Apu, Md Saiful Islam, Tanjim Taharat Aurpa, Sharad Hasan |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 49925 |
| LICENSE | CC_BY |
| RIGHTS | CC BY |
| SOURCE | PLOS |