anilguven commited on
Commit
6227da4
1 Parent(s): 885ee95

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +54 -1
README.md CHANGED
@@ -14,4 +14,57 @@ tags:
14
  - review
15
  - albert
16
  - bert
17
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  - review
15
  - albert
16
  - bert
17
+ ---
18
+ ### Model Info
19
+
20
+ This model was developed/finetuned for product review task for Turkish Language. Model was finetuned via hepsiburada.com product review dataset.
21
+ - LABEL_0: negative review
22
+ - LABEL_1: positive review
23
+
24
+ ### Model Sources
25
+
26
+ <!-- Provide the basic links for the model. -->
27
+
28
+ - **Dataset:** https://huggingface.co/datasets/anilguven/turkish_product_reviews_sentiment
29
+ - **Paper:** https://ieeexplore.ieee.org/document/9559007
30
+ - **Demo-Coding [optional]:** https://github.com/anil1055/Turkish_Product_Review_Analysis_with_Language_Models
31
+ - **Finetuned from model [optional]:** https://huggingface.co/loodos/albert-base-turkish-uncased
32
+ -
33
+
34
+ #### Preprocessing
35
+
36
+ You must apply removing stopwords, stemming, or lemmatization process for Turkish.
37
+
38
+ ### Results
39
+
40
+ - auprc = 0.9588538437395457
41
+ - auroc = 0.9653234951018236
42
+ - eval_loss = 0.37227460598843365
43
+ - fn = 188
44
+ - fp = 288
45
+ - mcc = 0.826593937301856
46
+ - tn = 2479
47
+ - tp = 2516
48
+ - Accuracy: %91.30
49
+
50
+ ## Citation
51
+
52
+ <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
53
+
54
+ **BibTeX:**
55
+
56
+ @INPROCEEDINGS{9559007,
57
+ author={Guven, Zekeriya Anil},
58
+ booktitle={2021 6th International Conference on Computer Science and Engineering (UBMK)},
59
+ title={The Effect of BERT, ELECTRA and ALBERT Language Models on Sentiment Analysis for Turkish Product Reviews},
60
+ year={2021},
61
+ volume={},
62
+ number={},
63
+ pages={629-632},
64
+ keywords={Computer science;Sentiment analysis;Analytical models;Computational modeling;Bit error rate;Time factors;Random forests;Sentiment Analysis;Language Model;Product Review;Machine Learning;E-commerce},
65
+ doi={10.1109/UBMK52708.2021.9559007}}
66
+
67
+
68
+ **APA:**
69
+
70
+ Guven, Z. A. (2021, September). The effect of bert, electra and albert language models on sentiment analysis for turkish product reviews. In 2021 6th International Conference on Computer Science and Engineering (UBMK) (pp. 629-632). IEEE.