Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
|
3 |
+
language: it
|
4 |
+
|
5 |
+
license: mit
|
6 |
+
|
7 |
+
tags:
|
8 |
+
|
9 |
+
- sentiment
|
10 |
+
|
11 |
+
- Italian
|
12 |
+
|
13 |
+
---
|
14 |
+
|
15 |
+
# FEEL-IT: Emotion and Sentiment Classification for the Italian Language
|
16 |
+
|
17 |
+
## Abstract
|
18 |
+
|
19 |
+
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?
|
20 |
+
|
21 |
+
An abundance of approaches has been introduced for tackling both tasks. However, at least for Italian, they all treat only one of the tasks at a time. We introduce FEEL-IT, a novel benchmark corpus of Italian Twitter posts annotated with four basic emotions: anger, fear, joy, sadness. By collapsing them, we can also do sentiment analysis. We evaluate our corpus on benchmark datasets for both emotion and sentiment classification, obtaining competitive results.
|
22 |
+
|
23 |
+
We release an open-source Python library, so researchers can use a model trained on FEEL-IT for inferring both sentiments and emotions from Italian text.
|
24 |
+
|
25 |
+
| Model | Download |
|
26 |
+
|
27 |
+
| ------ | ------ |
|
28 |
+
|
29 |
+
| `feel-it-italian-sentiment` | [Link](https://huggingface.co/MilaNLProc/feel-it-italian-sentiment) |
|
30 |
+
|
31 |
+
| `feel-it-italian-emotion` | [Link](https://huggingface.co/MilaNLProc/feel-it-italian-emotion) |
|
32 |
+
|
33 |
+
## Model
|
34 |
+
|
35 |
+
The feel-it-italian-emotion model performs emotion classification (joy, fear, anger, sadness). We fine-tuned the [UmBERTo model](https://huggingface.co/Musixmatch/umberto-commoncrawl-cased-v1) on our new dataset (i.e., FEEL-IT) obtaining state-of-the-art performances on different data sets.
|
36 |
+
|
37 |
+
## Data
|
38 |
+
|
39 |
+
Our data has been collected by annotating tweets from a broad range of topics. In total, we have 2037 tweets annotated with an emotion label. More details can be found in our paper.
|
40 |
+
|
41 |
+
## Performance
|
42 |
+
|
43 |
+
Soon
|
44 |
+
|
45 |
+
## Usage
|
46 |
+
|
47 |
+
```python
|
48 |
+
|
49 |
+
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
50 |
+
|
51 |
+
tokenizer = AutoTokenizer.from_pretrained("MilaNLProc/feel-it-italian-emotion")
|
52 |
+
|
53 |
+
model = AutoModelForSequenceClassification.from_pretrained("MilaNLProc/feel-it-italian-emotion")
|
54 |
+
|
55 |
+
```
|
56 |
+
|
57 |
+
## Citation
|
58 |
+
|
59 |
+
Please use the following bibtex entry if you use this model in your project:
|
60 |
+
|
61 |
+
```
|
62 |
+
|
63 |
+
@inproceedings{bianchi2021feel,
|
64 |
+
|
65 |
+
title = {{"FEEL-IT: Emotion and Sentiment Classification for the Italian Language"}},
|
66 |
+
|
67 |
+
author = "Bianchi, Federico and Nozza, Debora and Hovy, Dirk",
|
68 |
+
|
69 |
+
booktitle = "Proceedings of the 11th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis",
|
70 |
+
|
71 |
+
year = "2021",
|
72 |
+
|
73 |
+
publisher = "Association for Computational Linguistics",
|
74 |
+
|
75 |
+
}
|
76 |
+
|
77 |
+
```
|