Model Card: Sentiment Classifier (DistilBERT - SST-2)
Overview
This repository demonstrates sentiment classification using the pretrained distilbert-base-uncased-finetuned-sst-2-english model.
The model performs binary sentiment classification, labeling English text as either positive or negative. This project explores the use of an existing transformer-based NLP model for inference and applied text analysis.
Use Cases
With appropriate domain-specific evaluation, sentiment classification can be applied to tasks such as:
Analyzing reviews, comments, or other text
Exploring sentiment patterns in customer feedback
Comparing sentiment across groups or time periods
Supporting exploratory analysis of large text collections
Because the underlying model was fine-tuned on SST-2 movie-review data, performance should be evaluated before applying it to substantially different domains.
Example
Input: "This new update is amazing — so much faster!"
Output: Positive
Input: "This feature is broken and support isn't helping."
Output: Negative
---
## Strengths
- Extremely lightweight: good for mobile and low-latency use
- Fine-tuned on a benchmark sentiment dataset (SST-2)
- Strong out-of-the-box performance for informal English
---
## Limitations
Binary classification only: positive or negative
Does not represent neutral or more nuanced emotional states
The underlying model was fine-tuned on English movie-review data
Performance may differ substantially on other domains or writing styles
Sarcasm, ambiguity, cultural context, and domain-specific language may produce unreliable classifications
Results should not be assumed reliable for clinical, legal, safety-critical, or other high-stakes decisions without appropriate validation
---
## Model Details
Architecture: DistilBERT
Model used: distilbert-base-uncased-finetuned-sst-2-english
Fine-tuning dataset: SST-2 (Stanford Sentiment Treebank)
Task: Text classification
Classes: Positive, Negative
---
## Project Scope
This project uses an existing fine-tuned model rather than training or fine-tuning DistilBERT from scratch.
The purpose is to demonstrate hands-on use of transformer-based NLP for sentiment classification and to explore the capabilities and limitations of applying a pretrained classifier to text-analysis tasks.
---
## License
MIT License — free to use, adapt, and deploy commercially.
---
## Authorship Note
Underlying model: distilbert-base-uncased-finetuned-sst-2-english
This repository and its documentation were created by Sarah Mancinho as part of hands-on work with applied NLP and machine learning.
This model card was written by [Sarah Mancinho](https://huggingface.co/Sarah-h-h) as part of a public AI/LLM contribution series on Hugging Face.
Original model: [`distilbert-base-uncased-finetuned-sst-2-english`](https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english)
---
## Citation