Downloads · 30 days
7
15% of all-time downloads
moodshift-roberta-llm-augmented
Sarjinkhan2003/moodshift-roberta-llm-augmented
moodshift-roberta-llm-augmented is a text classification model from Sarjinkhan2003. Use it when you need a label for a piece of text.
Novel contribution: LLM-based minority class augmentation via Groq (llama-3.3-70b)
All-time downloads
48
Public
Repo size
511 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin511 MB · 99%
At a glance
- Task
- Text Classification
- Model type
- emotion_aware_roberta_esa_tfidf_focal_augmented
- Access
- Public
- Created
- Apr 30, 2026
- Updated
- Apr 30, 2026
- SHA
- 8dfc2e86
Try a prompt
Datasets
Model card
From the Hugging Face model README
MoodShift — RoBERTa+ESA+TF-IDF+FL with LLM Data Augmentation
Novel contribution: LLM-based minority class augmentation via Groq (llama-3.3-70b)
with self-consistency filtering for label fidelity.
Test Accuracy: 0.9265 | Macro F1: 0.8926
Baseline (no augmentation): Acc=0.9235 | F1=0.8831
ICCA 2026 HCI Research — MoodShift Adaptive Chatbot
- Task
- Text Classification
- Type
- emotion_aware_roberta_esa_tfidf_focal_augmented
- Created
- Apr 30, 2026
- Updated
- Apr 30, 2026