• Publications
  • Influence
Sentence-level sentiment analysis in Persian
TLDR
A sentence-level dataset for sentiment analysis in Persian, SPerSent, and a new Persian lexicon, CNRC are introduced and a well-known machine learning method, Naïve Bayes, is used to evaluate the S perSent.
ParsiNLU: A Suite of Language Understanding Challenges for Persian
TLDR
This work introduces ParsiNLU, the first benchmark in Persian language that includes a range of language understanding tasks—reading comprehension, textual entailment, and so on, and presents the first results on state-of-the-art monolingual and multilingual pre-trained language models on this benchmark and compares them with human performance.
The effect of aggregation methods on sentiment classification in Persian reviews
TLDR
The results on four Persian review data sets show that the review-level aggregation can improve rating classification, although this approach does not have a positive impact on polarity classification.
Evaluating a Multi-sense Definition Generation Model for Multiple Languages
TLDR
This study proposes a context-agnostic approach to definition modeling, based on multi-sense word embeddings, that is capable of generating multiple definitions for a target word.
HOMPer: A new hybrid system for opinion mining in the Persian language
TLDR
An exhaustive investigation of machine learning– and lexicon-based methods is performed and a new hybrid method is proposed for rating-prediction problem in the Persian language, demonstrating that this proposed method may also be successfully used for polarity detection.
Translation is not enough: Comparing Lexicon-based methods for sentiment analysis in Persian
TLDR
Four lexicons are compared to show the importance of lexicons in the performance of document-level sentiment analysis in Persian and results show that using just adjectives leads to higher results in comparison to using NRC.
Improving Sentiment Polarity Detection Through Target Identification
TLDR
The results of comparing the proposed method with a state-of-the-art lexicon-based method show that specifying the main targets of reviews can improve the performance of the systems about 17% and 12% in terms of accuracy and F1-measure.
Words Are Important
TLDR
A new hybrid method using both ML and the lexicon-based approach is presented in which PerLex words are used to train the ML algorithm, and the results demonstrate the excellence of using opinionated lexicon terms followed by bigrams as the features employed in the ML method.
Uninorm operators for sentence-level score aggregation in sentiment analysis
TLDR
A new sentence-level aggregation mechanism based on uninorm operators is proposed for aggregating sentence- level sentiment into an overall document-level opinion and implementation results show that the proposed method achieves a higher performance in polarity detection while the Dempster-Shafer method slightly outperforms the proposedmethod in score prediction task.