FarsiYar Text-Mining Group try to collect best resources for opinion mining in the Persian language.
Please participate in its development.
- 2020-DeepSentiPers: Deep Learning Models Plus Data Augmentation Methods in Persian Sentiment Analysis (codes, talk)
- 2019-Sentiment Analysis Challenges in Persian Language
- 2018-The Impact of Sentiment Features on the Sentiment Polarity Classification in Persian Reviews
- "PersianSWN" : (2017) HesNegar: Persian Sentiment WordNet
- "PerSent" : (2016) PerSent: A Freely Available Persian Sentiment Lexicon
- "LexiPers V1.0" : (2015) LexiPers: An ontology based sentiment lexicon for Persian
- "Lexicon-based Sentiment Analysis Data" : (2015) Lexicon-based Sentiment Analysis for Persian Text
- "UTIIS Sentiment GoldData" : (2014) Semi-supervised word polarity identification in resource-lean languages
- "SentiPers V1.0" : (2018) SentiPers: a sentiment analysis corpus for Persian
- "SentiFars" : (2019) SentiFars: A Persian Polarity Lexicon for Sentiment Analysis
You can download csv version of this resource from : "PersianSWN.csv".
Each line (entry) has 5 fields :
- Synset id (based on Princeton WordNet standard format):
IdNumber-PosTag
e.g. 00001740-a - Persian word.
- Confidence value (based on FerdowsNet WordNet).
- Positivity value.
- Negativity value.
Sample data:
00001740-a توانا 1.00 0.125 0.000
00051373-a توانا 0.45 0.375 0.250
00001740-a قادر 0.24 0.125 0.000
00002098-a عاجز 1.00 0.000 0.750
00051696-a عاجز 0.18 0.000 0.500
00002098-a ناتوان 0.75 0.000 0.750
00051696-a ناتوان 0.58 0.000 0.500
For more information, please visit our paper in the Signal and Data Processing Journal