Multilingual Sentiment Analysis using Deep-Learning Architectures

Dominic, Praveen; Purushothaman, Niranjan; Kumar, Anish Skanda Anil; Prabagaran, A; Blessy, J Angelin; John, A

doi:10.1109/icssit55814.2023.10060993

Cited by 8 publications

(10 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study by [108] employs deep learning, specifically the BERT transformer model, to conduct sentiment analysis on public opinions regarding the ongoing Russia-Ukraine war. Focusing on economic implications, non-English posts are translated to English using neural machine translation and Google Translator.…”

Section: B Pre-trained (Transformers)mentioning

confidence: 99%

“…Table 8 illustrates the analysis of the reviewed papers and underscores the significance of preprocessing stages in low-resource sentiment analysis tasks, with a particular emphasis on data cleaning as a present practice across the studies. However, The studies [48] and [108] were found to have used NER preprocessing step. Moreover, there is notable variation in the reporting of preprocessing steps, with certain studies such in a study like [64], [69], [70] failing to document any preprocessing steps.…”

Section: Transfer Learningmentioning

confidence: 99%

“…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],…”

Section: Transfer Learningmentioning

confidence: 99%

“…Lemmatization [62], [74], [104], [108] Part-of-speech (POS) [95], [67], [76], [108] Tokenization [47], [48], [51], [67], [74], [94], [100], [104],…”

Section: Transfer Learningmentioning

confidence: 99%

“…[80], [106], [53], [110], [83], [112], [113], [115], [116] Normalization [89], [77], [104], [80], [108], [83] Name Entity Reg (NER) [48], [108] N/A [64], [69], [70], [91], [84], [90], [101], [102], [127], [66] Table 9 Shows the analysis of the feature extraction method across reviewed studies in sentiment analysis for low-resource languages. The review reveals several trends.…”

Section: Transfer Learningmentioning

confidence: 99%

See 4 more Smart Citations

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

Aliyu,

Sarlan,

Usman Danyaro

et al. 2024

IEEE Access

View full text Add to dashboard Cite

The field of low-resource sentiment analysis has seen significant developments in recent years. This research review SLR evaluates the approaches and data sources utilized in low-resource sentiment analysis by deep learning. The primary aim is to discover suitable approaches for future sentiment analysis in low-resource. Our studies explore various languages, models, and data sources expressing a desire to create effective approaches. Our emphasis lies in the critical evaluation of the approaches and the datasets utilized, to identify areas where further research is needed. Our analysis study adds to the existing body of literature reviews, encompassing multilingual low-resource sentiment analysis research spanning from 2018 to 2023. The findings indicate that the transfer learning approach is the most frequently used, followed by word embedding learning and machine translation systems. Additionally, the study shows that social media is the most used platform for data collection, followed by product reviews, movies, and hotels. There has been a significant surge in the adoption of pre-trained transformers, indicating a growing interest in exploring the potential of these models for low-resource languages within the natural language processing (NLP) community. This trend is largely attributed to the novel nature of these models and their feature of being nonlabour intensive. However, the scarcity of annotated datasets for such languages remains a major hurdle. finally, these research findings are relevant and informative for any researcher working in the field of lowresource multilingual sentiment analysis. The study introduces a conceptual framework for performing sentiment analysis in low-resource. The study provides a valuable resource for future researchers.

show abstract

Section: B Pre-trained (Transformers)mentioning

confidence: 99%

Section: Transfer Learningmentioning

confidence: 99%

Section: Transfer Learningmentioning

confidence: 99%

“…Lemmatization [62], [74], [104], [108] Part-of-speech (POS) [95], [67], [76], [108] Tokenization [47], [48], [51], [67], [74], [94], [100], [104],…”

Section: Transfer Learningmentioning

confidence: 99%

Section: Transfer Learningmentioning

confidence: 99%

See 3 more Smart Citations

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

Aliyu,

Sarlan,

Usman Danyaro

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

Augmenting sentiment prediction capabilities for code-mixed tweets with multilingual transformers

Hashmi,

Yayilgan,

Shaikh

2024

Soc. Netw. Anal. Min.

View full text Add to dashboard Cite

People in the modern digital era are increasingly embracing social media platforms to express their concerns and emotions in the form of reviews or comments. While positive interactions within diverse communities can considerably enhance confidence, it is critical to recognize that negative comments can hurt people’s reputations and well-being. Currently, individuals tend to express their thoughts in their native languages on these platforms, which is quite challenging due to potential syntactic ambiguity in these languages. Most of the research has been conducted for resource-aware languages like English. However, low-resource languages such as Urdu, Arabic, and Hindi present challenges due to limited linguistic resources, making information extraction labor-intensive. This study concentrates on code-mixed languages, including three types of text: English, Roman Urdu, and their combination. This study introduces robust transformer-based algorithms to enhance sentiment prediction in code-mixed text, which is a combination of Roman Urdu and English in the same context. Unlike conventional deep learning-based models, transformers are adept at handling syntactic ambiguity, facilitating the interpretation of semantics across various languages. We used state-of-the-art transformer-based models like Electra, code-mixed BERT (cm-BERT), and Multilingual Bidirectional and Auto-Regressive Transformers (mBART) to address sentiment prediction challenges in code-mixed tweets. Furthermore, results reveal that mBART outperformed the Electra and cm-BERT models for sentiment prediction in code-mixed text with an overall F1-score of 0.73. In addition to this, we also perform topic modeling to uncover shared characteristics within the corpus and reveal patterns and commonalities across different classes.

show abstract

A novel ChatGPT-based multimodel framework for tourism review mining: a case study on China’s five sacred mountains

Cheng,

Chen,

Wang

et al. 2024

JHTT

View full text Add to dashboard Cite

Purpose This study aims to introduce an innovative framework for mining tourism reviews that not only excels in sentiment analysis accuracy but also prioritizes user-friendly design for enhanced usability. Design/methodology/approach Online reviews of China’s Five Sacred Mountains were analyzed using an integrated methodology. Sentiment analysis was performed using ChatGPT, bidirectional encoder representations from transformers (BERT) and convolutional neural networks, with ChatGPT demonstrating superior performance. Latent Dirichlet allocation extracted key attributes. Models including importance–performance analysis (IPA), asymmetric impact-performance analysis (AIPA) and importance–performance competitor analysis (IPCA) then synthesized findings. Findings The results demonstrate that ChatGPT outperforms both machine learning and lexicon-based models in sentiment recognition, exhibiting performance comparable to that of the BERT model. In the case study, integrating sentiment analysis outcomes with IPA reveals deficiencies in both topics and attributes. Moreover, the synergistic combination of IPA, AIPA and IPCA furnishes actionable recommendations for resource management and enables nuanced monitoring of sustainability attributes. Practical implications Leveraging this framework in conjunction with the ChatGPT platform for application development can bring practical convenience to the tourism industry. It supports sentiment analysis, topic categorization and opinion mining. Equipped with monitoring capabilities, it provides valuable insights for sustainable improvement, aiding managers in formulating effective marketing strategies. Originality/value This research develops a novel multimodel framework integrating various ML/DL techniques and business models in a synergistic way. It provides an innovative and highly accurate yet simple approach to tourism review mining and enhances accessibility of advanced artificial intelligence for sustainable tourism monitoring, addressing limitations of prior methods.

show abstract

Multilingual Sentiment Analysis using Deep-Learning Architectures

Cited by 8 publications

References 6 publications

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

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

Augmenting sentiment prediction capabilities for code-mixed tweets with multilingual transformers

A novel ChatGPT-based multimodel framework for tourism review mining: a case study on China’s five sacred mountains

Contact Info

Product

Resources

About