SOTAVerified

BanglaBook: A Large-scale Bangla Dataset for Sentiment Analysis from Book Reviews

2023-05-11Code Available1· sign in to hype

Mohsinul Kabir, Obayed Bin Mahfuz, Syed Rifat Raiyan, Hasan Mahmud, Md Kamrul Hasan

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

The analysis of consumer sentiment, as expressed through reviews, can provide a wealth of insight regarding the quality of a product. While the study of sentiment analysis has been widely explored in many popular languages, relatively less attention has been given to the Bangla language, mostly due to a lack of relevant data and cross-domain adaptability. To address this limitation, we present BanglaBook, a large-scale dataset of Bangla book reviews consisting of 158,065 samples classified into three broad categories: positive, negative, and neutral. We provide a detailed statistical analysis of the dataset and employ a range of machine learning models to establish baselines including SVM, LSTM, and Bangla-BERT. Our findings demonstrate a substantial performance advantage of pre-trained models over models that rely on manually crafted features, emphasizing the necessity for additional training resources in this domain. Additionally, we conduct an in-depth error analysis by examining sentiment unigrams, which may provide insight into common classification errors in under-resourced languages like Bangla. Our codes and data are publicly available at https://github.com/mohsinulkabir14/BanglaBook.

Tasks

Benchmark Results

DatasetModelMetricClaimedVerifiedStatus
BanglaBookBangla-BERT (large)Weighted Average F1-score0.93Unverified
BanglaBookRandom Forest (word 2-gram + word 3-gram)Weighted Average F1-score0.91Unverified
BanglaBookBangla-BERT (base-uncased)Weighted Average F1-score0.91Unverified
BanglaBookSVM (word 2-gram + word 3-gram)Weighted Average F1-score0.91Unverified
BanglaBookRandom Forest (word 1-gram)Weighted Average F1-score0.9Unverified
BanglaBookLogistic Regression (char 2-gram + char 3-gram)Weighted Average F1-score0.9Unverified
BanglaBookLogistic Regression (word 2-gram + word 3-gram)Weighted Average F1-score0.9Unverified
BanglaBookXGBoost (char 2-gram + char 3-gram)Weighted Average F1-score0.87Unverified
BanglaBookMultinomial NB (word 2-gram + word 3-gram)Weighted Average F1-score0.87Unverified
BanglaBookXGBoost (word 2-gram + word 3-gram)Weighted Average F1-score0.87Unverified
BanglaBookMultinomial NB (BoW)Weighted Average F1-score0.86Unverified
BanglaBookSVM (word 1-gram)Weighted Average F1-score0.85Unverified
BanglaBookLSTM (GloVe)Weighted Average F1-score0.1Unverified

Reproductions