| | --- |
| | language: |
| | - en |
| | metrics: |
| | - accuracy |
| | library_name: transformers |
| | pipeline_tag: text-classification |
| | tags: |
| | - finance |
| | widget: |
| | - text: "The semiconductor market is seeing an unprecedented growth this year." |
| | - text: "Due to the recent chip shortages, prices for electronics have increased." |
| | - text: "As the AI blooms, major semiconductor manufacturers are ramping up production to meet demand." |
| | - text: "Investors are wary of the semiconductor industry due to market volatility." |
| | --- |
| | # Model Name |
| | SFinBERT |
| |
|
| | ## Description |
| | This is part of Dissertaion Project of University of Glasgow MSc Software development Course |
| |
|
| | Utilizing the power of FinBERT, a model specifically trained for financial sentiment analysis, this tool adapts the foundational knowledge of FinBERT through transfer learning to cater to the semiconductor industry's nuances. |
| | It's designed to analyze financial news sentiment uniquely tailored to the semiconductor sector, enabling a more precise interpretation of news impacts within this domain. |
| | Harnessing both financial and semiconductor-specific insights, this sentiment analyzer offers a refined perspective, making it an essential tool for stakeholders, analysts, and enthusiasts in the semiconductor realm. |
| |
|
| | ```python |
| | from transformers import AutoTokenizer, AutoModelForSequenceClassification |
| | |
| | tokenizer = AutoTokenizer.from_pretrained("Yt99/SFinBERT") |
| | model = AutoModelForSequenceClassification.from_pretrained("Yt99/SFinBERT") |
| | |
| | text = "Your example text here." |
| | inputs = tokenizer(text, return_tensors="pt") |
| | outputs = model(**inputs) |
| | ``` |
| |
|
| | ## Acknowledgments |
| | Thanks to my supervisor, family and friends for supporting my work. |
