douglasgoodwin commited on
Commit
29906fc
·
verified ·
1 Parent(s): c186ccf
Files changed (1) hide show
  1. README.md +42 -14
README.md CHANGED
@@ -1,14 +1,42 @@
1
- ---
2
- title: Sentimentanalysis
3
- emoji: 👀
4
- colorFrom: green
5
- colorTo: green
6
- sdk: gradio
7
- sdk_version: 5.12.0
8
- app_file: app.py
9
- pinned: false
10
- license: cc0-1.0
11
- short_description: '6 emotions: sadness, joy, love, anger, fear, and suprise'
12
- ---
13
-
14
- Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # README.md
2
+ # Emotion Detection with DistilBERT
3
+
4
+ This Huggingface Space demonstrates emotion detection using the DistilBERT model fine-tuned for emotion classification. The model can detect six emotions: sadness, joy, love, anger, fear, and surprise.
5
+
6
+ ## Model Details
7
+
8
+ This app uses the `bhadresh-savani/distilbert-base-uncased-emotion` model, which is a fine-tuned version of DistilBERT specifically trained for emotion detection. The model was trained on a dataset containing text samples labeled with six different emotions.
9
+
10
+ ## Usage
11
+
12
+ 1. Enter any text in the input box
13
+ 2. Click "Submit" or press Enter
14
+ 3. The model will analyze the text and display the probability distribution of detected emotions
15
+ 4. Try the example inputs to see how the model performs on different types of text
16
+
17
+ ## Examples
18
+
19
+ The app includes several example inputs to demonstrate different emotional expressions. You can click on any example to see how the model interprets various emotional statements.
20
+
21
+ ## Limitations
22
+
23
+ - The model works best with English text
24
+ - Short to medium-length texts (1-3 sentences) typically work better than very long passages
25
+ - The model may not capture complex or mixed emotions perfectly
26
+ - Results are probabilistic and should be interpreted as the model's confidence in each emotion category
27
+
28
+ ## Setup Instructions
29
+
30
+ 1. Create a new Space on Huggingface:
31
+ - Go to huggingface.co/spaces
32
+ - Click "Create new Space"
33
+ - Choose "Gradio" as the SDK
34
+ - Select "Public" or "Private" visibility
35
+ - Name your space
36
+
37
+ 2. Upload these files to your Space:
38
+ - app.py
39
+ - requirements.txt
40
+ - README.md
41
+
42
+ The Space will automatically build and deploy your emotion detection app!