Italian emotion labels
According to the model card, the model performs emotion classification over joy, fear, anger, and sadness on Italian text.
Open Source Model Profile · MilaNLProc
feel-it-italian-emotion
feel-it-italian-emotion is a text-classification fine-tune from MilaNLProc. According to the model card, it classifies Italian text into joy, fear, anger, and sadness using the FEEL-IT corpus.
- Publisher
- MilaNLProc
- Task
- text-classification
- Model type
- camembert
- License
- Unknown
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
feel-it-italian-emotion is published by MilaNLProc as a Transformers text-classification model. The captured configuration identifies CamembertForSequenceClassification with model type camembert. According to the model card, it is a fine-tune on the FEEL-IT corpus of Italian Twitter posts for emotion and sentiment classification, with a companion FEEL-IT Python package documented.
Recorded capabilities
FEEL-IT corpus
The publisher describes FEEL-IT as a benchmark corpus of Italian Twitter posts annotated with four basic emotions, collapsible into sentiment labels.
Reported MultiEmotions-It numbers
The model card reports Macro-F1 0.57 and accuracy 0.73 after FEEL-IT training on MultiEmotions-It, against an MFC baseline of 0.20 and 0.64.
Classification stack
Captured configuration identifies CamembertForSequenceClassification with camembert model type and Transformers library support.
Use cases in the source record
- Italian emotion classification over the publisher's joy, fear, anger, and sadness labels.
- Italian sentiment analysis by collapsing the four emotion labels, as described by the publisher.
- Research use through the documented FEEL-IT Python package interface over Hugging Face models.
Limitations and unknowns
- No parameter count was extracted for this record.
- No license value was extracted for this record.
- Performance figures are publisher-reported card claims only and have not been independently verified by Ethen.
- The captured config reports camembert while the card describes an UmBERTo fine-tune; Ethen has not independently reconciled this naming.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: MilaNLProc/feel-it-italian-emotion
Captured: Unknown. Processed: 2026-09-07T19:34:34.415755+00:00.
FEEL-IT: Emotion and Sentiment Classification for the Italian Language FEEL-IT Python Package You can find the package that uses this model for emotion and sentiment classification here it is meant to be a very simple interface over HuggingFace models. License Users should refer to the following license Abstract Sentiment analysis is a common task to understand people's reactions online. Still, we often need more nuanced information: is the post negative because the user is angry or because they are sad? An abundance of approaches has been introduced for tackling both tasks. However, at least for Italian, they all treat only one of…
F001F002F003F004F005F006F007F008F009F011F012F013F014F015