Sentiment Polarity Detection on Bengali Book Reviews Using Multinomial Naïve Bayes

Hossain, Eftekhar; Sharif, Omar; Hoque, Mohammed Moshiul

doi:10.1007/978-981-33-4299-6_23

Cited by 36 publications

(14 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As it takes the result in the right direction (Qiu & Li, 2016), that's why it should be considered positive and negative sentiment. In the research of (Sharif, 2019), (Tabassum, 2019), (Chowdhury, 2014), (Khan, 2020), (Alam, 2017), (Islam K. I., 2020), (Islam M. S., 2016), (Hassan, 2016), (Abdullah Aziz Sharfuddin, 2018), (Tuhin et al, 2019), (Hossain et al, 2021) .They didn't introduce the neutral class in their proposed method.…”

Section: Rq2: What Are the Limitations Of The Existing Research Method?mentioning

confidence: 99%

“…But in the research of (Prasad et al, 2017) , (Tripto & Ali, 2018) , (Mahmudun et al, 2016), (Chowdhury & Chowdhury, 2014), (Hasan et al, 2014), (Sazzed & Jayarathna, 2019), (Khan et al, 2020), (K. I. Islam et al, 2020), (Sarkar & Bhowmick, 2018), (Alam et al, 2018), [26], (Hassan et al, 2017), (Aziz Sharfuddin et al, 2018), (Tuhin et al, 2019), Arafin Mahtab et al, 2018), (Hossain et al, 2021) they didn't apply this rule. As a result, if any sentence contains negation after negative that will not be considered positive together.…”

Section: Rq2: What Are the Limitations Of The Existing Research Method?mentioning

confidence: 99%

See 1 more Smart Citation

A Systematic Review of Sentiment Analysis from Bengali Text using NLP

Hira¹,

Akhond²,

Chowdhury³

et al. 2022

Am. J. Agric. Sci. Eng. Technol.

View full text Add to dashboard Cite

Sentiment Analysis (SA) is the method of studying a person’s comments and statements through computational means. It is a sub-domain of Natural Language Processing. A sentiment analysis (SA) system is created by training a significant number of positive, negative or neutral sentence datasets. Although there are many research papers on this subject in English, the work of sentiment analysis in Bengali has not become very popular due to the complexity of the Bangla language and the insufficient presence of the Bangla language online. But now the use of Bengali language has increased in online news, social media, and blogs. At the same time, the number of researches on Bengali NLP is also increasing. But what is the current state of sentiment analysis, its limitations and is there still room for improvement in some places, are not being properly reviewed and research is lagging behind. We have conducted a review on sentiment analysis so that future researchers of sentiment analysis can easily find out about the current state of sentiment analysis. In this research, we have tried to survey the current context of sentiment analysis (SA) and at the same time, we have created a sequence of comparatively better research from the existing ones. To create this sequence we followed a method called is TOPSIS. We have also discussed the challenges to overcome for improving the Sentiment analyzer.

show abstract

Section: Rq2: What Are the Limitations Of The Existing Research Method?mentioning

confidence: 99%

Section: Rq2: What Are the Limitations Of The Existing Research Method?mentioning

confidence: 99%

A Systematic Review of Sentiment Analysis from Bengali Text using NLP

Hira¹,

Akhond²,

Chowdhury³

et al. 2022

Am. J. Agric. Sci. Eng. Technol.

View full text Add to dashboard Cite

show abstract

“…The performance of these models is not very impressive as they were unable to capture semantic and contextual information in the text. The major obstacles are the inherent ambiguity of the language, the computational complexity of exploring large amounts of content, resource-poor language problems, and the contextual understanding of natural language (Zhou et al, 2021;Hossain et al, 2021b). Different DL models were applied to Malayalam tweets to classify them into positive and negative where Gated Recurrent Unit (GRU) achieved the highest accuracy (Soumya and Pramod, 2019).…”

Section: Related Workmentioning

confidence: 99%

CUET-NLP@DravidianLangTech-ACL2022: Exploiting Textual Features to Classify Sentiment of Multimodal Movie Reviews

Mustakim¹,

Jannat²,

Hasan³

et al. 2022

Proceedings of the Second Workshop on Speech and Language Technologies for Dravidian Languages

Self Cite

View full text Add to dashboard Cite

With the proliferation of internet usage, a massive growth of consumer-generated content on social media has been witnessed in recent years that provide people's opinions on diverse issues. Through social media, users can convey their emotions and thoughts in distinctive forms such as text, image, audio, video, and emoji, which leads to the advancement of the multimodality of the content users on social networking sites. This paper presents a technique for classifying multimodal sentiment using the text modality into five categories: highly positive, positive, neutral, negative, and highly negative. A shared task was organized to develop models that can identify the sentiments expressed by the videos of movie reviewers in both Malayalam and Tamil languages. This work applied several machine learning (LR, DT, MNB, SVM) and deep learning (BiLSTM, CNN+BiLSTM) techniques to accomplish the task. Results demonstrate that the proposed model with the decision tree (DT) outperformed the other methods and won the competition by acquiring the highest macro f 1 -score of 0.24.

show abstract

“…For the first type of sentiment classification method mentioned above, the sentiment of texts is analyzed by adopting traditional classifiers, such as support vector machines (SVM), random forests, multinomial naïve Bayes (mNB), and other models. e related literature on these methods are [14][15][16]. In these traditional methods, the types of classifiers are different, while the features adopted are similar, which are not fully utilized, resulting in a limited recognition rate.…”

Section: Introductionmentioning

confidence: 99%

Deep-Learning-Based Financial Message Sentiment Classification in Business Management

Shao

Chen

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

A deep-learning-based financial text sentiment classification method is proposed in this paper, which can provide a reference for business management. In the proposed method, domain adaptation is adopted to solve the common problem of insufficient labeled samples in the financial textual domain. Specifically, in the classification process, the seq2seq model is firstly adopted to extract the abstract from the financial message, which can reduce the influence of invalid information and speed up processing. In the process of sentiment classification, a bidirectional LSTM model is adopted for classification, which can more comprehensively make use of context information. Experiments are carried out to testify the proposed method through the open-source data set. It can be seen that the proposed method can effectively transfer from the reduced Amazon data set to the StockTwits financial text data set. Compared with the parameter-frozen-based method and the SDA-based method, the recognition rates have improved by 0.5% and 6.8%, respectively. If the target domain data set can be directly adopted for training, the recognition rate of the proposed method is higher than that of the SVM method and the LSTM method by 8.3% and 4.5%, respectively.

show abstract

Sentiment Polarity Detection on Bengali Book Reviews Using Multinomial Naïve Bayes

Cited by 36 publications

References 20 publications

A Systematic Review of Sentiment Analysis from Bengali Text using NLP

A Systematic Review of Sentiment Analysis from Bengali Text using NLP

CUET-NLP@DravidianLangTech-ACL2022: Exploiting Textual Features to Classify Sentiment of Multimodal Movie Reviews

Deep-Learning-Based Financial Message Sentiment Classification in Business Management

Contact Info

Product

Resources

About