Data-Augmentation for Bangla-English Code-Mixed Sentiment Analysis: Enhancing Cross Linguistic Contextual Understanding

Abstract

In today's digital world, automated sentiment analysis from online reviews can contribute to a wide variety of decision-making processes. One example is examining typical perceptions of a product based on customer feedbacks to have a better understanding of consumer expectations, which can help enhance everything from customer service to product offerings. Online review comments, on the other hand, frequently mix different languages, use non-native scripts and do not adhere to strict grammar norms. For a low-resource language like Bangla, the lack of annotated code-mixed data makes automated sentiment analysis more challenging. To address this, we collect online reviews of different products and construct an annotated Bangla-English code mix (BE-CM) dataset (Dataset and other resources are available at https://github.com/fokhruli/CM-seti-anlysis). On our sentiment corpus, we also compare several alternative models from the existing literature. We present a simple but effective data augmentation method that can be utilized with existing word embedding algorithms without the need for a parallel corpus to improve cross-lingual contextual understanding. Our experimental results suggest that training word embedding models (e.g., Word2vec, FastText) with our data augmentation strategy can help the model in capturing the cross-lingual relationship for code-mixed sentences, thereby improving the overall performance of existing classifiers in both supervised learning and zero-shot cross-lingual adaptability. With extensive experimentations, we found that XGBoost with Fasttext embedding trained on our proposed data augmentation method outperforms other alternative models in automated sentiment analysis on code-mixed Bangla-English dataset, with a weighted F1 score of 87%.INDEX TERMS Code mixed, sentiment analysis, Bangla-English corpus, bi-lingual, zero-shot learning.

Sentiment Analysis in Low-Resource Settings: A Comprehensive Review of Approaches, Languages, and Data Sources

“…One-hot encoding [35], [74] CBOW [96], , [97], [64], [68], [89], [75], [104] Skip Gram [80], [62], [68], [89] Embedding [89], [83], [69], [70], [91], [84], [127], [81],…”

“…Nonetheless, challenges persist, particularly in accurately representing all languages within tokenizer frameworks due to variations in language characters and other linguistic factors. Data cleaning [95], [35], [96], [49], [62], [65], [58], [68], [67], [89], [74], [75], [76], [77], [88], [94], [100], [103], [104], [107], [80], [106], [81], [108], [109], [82], [53], [110], [111], [83], [92], [113], [114], [115], [116], [117] Stemming [51], [67], [104], [108],…”

“…Notably, most studies reveal a predominance of social media as the primary source such in studies like [95], [113], [116], [80], [62] with 27 instances recorded. Other domains, such as product reviews [69] and [100], web content [81] and [101] , news [96] and [75], movies [106], hotels [68] and [97], tourism [48], and sports [35] are also represented, although with fewer occurrences. The utilization of multiple domains of data sources such as in [90], [67], [84], [70] is crucial as it allows for a comprehensive evaluation of proposed models across diverse contexts and datasets, enhancing the generalizability and robustness of the findings.…”

Challenges and Opportunities of Text-Based Emotion Detection: A Survey

“…They gathered high-quality code-mixed Bangla-English data from the Google Play Store by using a web scraping tool. There were about 970,852 samples taken in total [102].…”

SentMix-3L: A Novel Code-Mixed Test Dataset in Bangla-English-Hindi for Sentiment Analysis

“…However, a lot of the data are purely in Bangla and they only experiment using the BERT and multilingual BERT model (Devlin et al, 2019) while only providing development accuracy as the performance metric. Another recent work by Tareq et al (2023), consists of 18,074 Bangla-English Code-mixed data from online for the purpose of sentiment analysis. They augment the dataset using their own approach and achieve their best result of an 87% weighted F1 score by implementing XGBoost with Fasttext embedding.…”