[Day 9] A local Japanese sentiment AI (BERT) read 8 years of a LINE chat, and the ups and downs surfaced from numbers alone
![[Day 9] A local Japanese sentiment AI (BERT) read 8 years of a LINE chat, and the ups and downs surfaced from numbers alone](/img-proxy?url=https%3A%2F%2Fmedia2.dev.to%2Fdynamic%2Fimage%2Fwidth%3D1200%2Cheight%3D627%2Cfit%3Dcover%2Cgravity%3Dauto%2Cformat%3Dauto%2Fhttps%253A%252F%252Fraw.githubusercontent.com%252FSAETAG%252Fdgx-100-experiments-images%252Fmain%252Fday09-line-relationship%252F01-story.png&w=1024)
A local Japanese sentiment AI analyzed eight years of LINE chat history to uncover emotional trends. The analysis focused on message volume and tone rather than the content of the messages. Results showed distinct phases in the conversation, including periods of silence and changes in emotional tone over time.
- ▪The AI processed 87,621 total messages over eight years, including 66,329 text messages.
- ▪The analysis revealed a clear arc in the conversation, with phases of increased activity and silence.
- ▪Tone scoring indicated that the mood of the conversation declined before periods of silence.
Opening excerpt (first ~120 words) tap to expand
try { if(localStorage) { let currentUser = localStorage.getItem('current_user'); if (currentUser) { currentUser = JSON.parse(currentUser); if (currentUser.id === 3910738) { document.getElementById('article-show-container').classList.add('current-user-is-article-author'); } } } } catch (e) { console.error(e); } PEPPERCORN Posted on May 29 [Day 9] A local Japanese sentiment AI (BERT) read 8 years of a LINE chat, and the ups and downs surfaced from numbers alone #localllm #ai #dgxspark #privacy 100 Experiments with DGX (9 Part Series) 1 [Day 1] DGX Spark Came Home — I Made It Draw a Cat 2 [Day 2] I Trained an AI on 22 Photos of My Cat — Now It Draws Her in Any Scene ... 5 more parts...
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at DEV.to (Top).
Discussion
0 commentsMore from DEV.to (Top)
