Sentiment Analysis of Informal Persian Texts Using Embedding Informal words and Attention-Based LSTM Network

Karrabi, Mohammad; Oskooie, Leila; Bakhtiar, Mohsen; Farahani, Mohammad Ali Davood Abadi; Monsefi, Reza

doi:10.1109/cfis49607.2020.9238699

Cited by 10 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The former, where the corpus includes a large quantity of words, does not necessitate a label for each comment. However, according to [9], a significant drawback of these algorithms is their inefficiency when dealing with complex texts. This shortcoming contributes to the popularity of the latter algorithm in sentiment analysis problems, prompting numerous Seyed Jamal Haddadi a, * , Elham Khoeini b , Pezhman Salmani c , Mehdi Beygi d , Mehrdad Haddad Khoshkar e a-Postdoctoral Researcher at Institute of Computing, University of Campinas, Brazil, jamal.haddadi88@gmail.com b-Department of Information Technology and Infrastructure Governance, Bank Pasargad, e.khoeini@gmail.com c-Department of Information Technology and Infrastructure Governance, Bank Pasargad, Iran, pejman.salmani94@gmail.com d-Department of Information Technology and Infrastructure Governance, Bank Pasargad, Iran, soheil.hadadi@gmail.com e-Department of Information Technology and Infrastructure Governance, Bank Pasargad, Iran, m.s1988.haddadi@gmail.com * Corresponding Author Email: Jamal.haddadi88@gmail.com researchers to devise and apply various DNNs-based classification algorithms such as pre-trained word embedding and language modeling.…”

Section: Introductionmentioning

confidence: 99%

“…The significance of this vector becomes apparent when used as an input for a deep learning neural network. Consequently, Word2Vec [9] and GloVe (Global Vectors for Word Representation) [11] have garnered substantial attention among researchers, becoming the most renowned pre-trained word embeddings strategies based on Neural Networks (NNs) for generating word representation vectors.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Persian Sentiment Analysis via a Transformer Model concerning Banking Sector

Haddadi,

Khoeini,

Salmani

et al. 2023

Preprint

View full text Add to dashboard Cite

The competitive landscape of a country's banking sector necessitates an in-depth understanding of customer satisfaction levels concerning the services provided. Presently, customers predominantly express their feedback via social media platforms in the form of posts and comments. This study endeavors to create a highly accurate sentiment detection algorithm for the Iranian banking system, utilizing a transformer model. In the initial stages, we collected data by crawling comments from Twitter, which are subsequently labeled and filtered according to the names of Iranian banks, dating from 2019. Following this, an optimized Deep Neural Network (DNN)-based pre-trained ParsBERT model, a monolingual Persian model, is fine-tuned using this data. Finally, our model is evaluated on a test dataset, and the results are validated by comparing them with the original multilingual BERT, Bidirectional Long Short-Term Memory (Bi-LSTM) network, and four other classification methods. To address the Out-Of-Vocabulary (OOV) issue, a character-level embedding is incorporated in conjunction with the word-level embedding. This approach aids in tackling the multitude of variations observed in non-native words, extracting character-level features using a character-level Bi-LSTM. The proposed model highlights the statistical superiority of our method when compared to the other methods evaluated.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%