Update README.md
Browse files
README.md
CHANGED
|
@@ -15,4 +15,53 @@ tags:
|
|
| 15 |
- emotion
|
| 16 |
- sentiment
|
| 17 |
- bert
|
| 18 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
- emotion
|
| 16 |
- sentiment
|
| 17 |
- bert
|
| 18 |
+
---
|
| 19 |
+
### Model Info
|
| 20 |
+
|
| 21 |
+
This model was developed/finetuned for tweet emotion detection task for the Turkish Language. This model was finetuned via tweet dataset. This dataset contains 5 classes: angry, happy, sad, surprised and afraid.
|
| 22 |
+
- LABEL_0: angry
|
| 23 |
+
- LABEL_1: afraid
|
| 24 |
+
- LABEL_2: happy
|
| 25 |
+
- LABEL_3: surprised
|
| 26 |
+
- LABEL_4: sad
|
| 27 |
+
|
| 28 |
+
### Model Sources
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Dataset:** https://huggingface.co/datasets/anilguven/turkish_tweet_emotion_dataset
|
| 33 |
+
- **Paper:** https://ieeexplore.ieee.org/document/9559014
|
| 34 |
+
- **Demo-Coding [optional]:** https://github.com/anil1055/Turkish_tweet_emotion_analysis_with_language_models
|
| 35 |
+
- **Finetuned from model [optional]:** https://huggingface.co/dbmdz/distilbert-base-turkish-cased
|
| 36 |
+
|
| 37 |
+
#### Preprocessing
|
| 38 |
+
|
| 39 |
+
You must apply removing stopwords, stemming, or lemmatization process for Turkish.
|
| 40 |
+
|
| 41 |
+
### Results
|
| 42 |
+
|
| 43 |
+
- eval_loss = 0.05249839214870008
|
| 44 |
+
- mcc = 0.9828118433102754
|
| 45 |
+
- Accuracy: %98.63
|
| 46 |
+
|
| 47 |
+
## Citation
|
| 48 |
+
|
| 49 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 50 |
+
|
| 51 |
+
**BibTeX:**
|
| 52 |
+
|
| 53 |
+
*@INPROCEEDINGS{9559014,
|
| 54 |
+
author={Guven, Zekeriya Anil},
|
| 55 |
+
booktitle={2021 6th International Conference on Computer Science and Engineering (UBMK)},
|
| 56 |
+
title={Comparison of BERT Models and Machine Learning Methods for Sentiment Analysis on Turkish Tweets},
|
| 57 |
+
year={2021},
|
| 58 |
+
volume={},
|
| 59 |
+
number={},
|
| 60 |
+
pages={98-101},
|
| 61 |
+
keywords={Computer science;Sentiment analysis;Analytical models;Social networking (online);Computational modeling;Bit error rate;Random forests;Sentiment Analysis;BERT;Machine Learning;Text Classification;Tweet Analysis.},
|
| 62 |
+
doi={10.1109/UBMK52708.2021.9559014}}*
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
**APA:**
|
| 66 |
+
|
| 67 |
+
*Guven, Z. A. (2021, September). Comparison of BERT models and machine learning methods for sentiment analysis on Turkish tweets. In 2021 6th International Conference on Computer Science and Engineering (UBMK) (pp. 98-101). IEEE.*
|