Transfer learning and sentiment analysis of Bahraini dialects sequential text data using multilingual deep learning approach

Omran, Thuraya; Sharif, Baraa T.; Grosan, Crina; Li, Yongmin

doi:10.1016/j.datak.2022.102106

“…Advanced Bracket Model (BERT), are designed to estimate numerous of the presently available operations for tweet preprocessing, in terms of the statistical significance of their impact on sentiment analysis performance. In addition, data available in two languages, videlicet English and Italian, are considered to assess language dependence [13].…”

Section: Detailed Literaturementioning

confidence: 99%

“…It was presented at the EVALITA 2016 conference, which evaluated NLP and voice tools for Italian. [13].…”

Section: Referencesmentioning

confidence: 99%

Multilingual Sentiment Analysis Using Deep Learning: Survey

Ihsan,

Ashraf,

Jhanjhi

2023

Preprint

0

View full text Add to dashboard Cite

The rise of the Internet has enabled people to express their opinions on various subjects through social media, blogs, and website comments. As a result, there has been a significant increase in research on sentiment analysis. However, most of the research efforts have focused on analyzing sentiment in English-language data, neglecting the wealth of information available in other languages. In this paper, we provide a comprehensive review of the current state-of-the-art in multilingual sentiment analysis. The survey investigates techniques for data preprocessing, representation learning, and feature extraction in multilingual sentiment analysis. It explores cross-lingual transfer learning, domain adaptation, and data augmentation methods that enhance the performance of sentiment analysis models, particularly in low-resource languages and domains. It provides insights into the state-of-the-art approaches, challenges, and opportunities in this evolving field and encourages further advancements in multilingual sentiment analysis research.

show abstract

“…Text analytics technology is a method to systematically analyze and understand text data by extracting and processing linguistic features, entities, emotions, and themes in the text to provide applications such as decision support, sentiment analysis, and public opinion monitoring. Today, we are going to use text analytics to explore themes and patterns in American literature [1][2][3].…”

Section: Introductionmentioning

confidence: 99%

Exploring Themes and Patterns in American Literature Using Text Analysis Techniques

Cao

2024

Applied Mathematics and Nonlinear Sciences

0

View full text Add to dashboard Cite

This study leverages web crawling techniques within the realm of text mining to collect text data from American literary sources. Given the presence of substantial extraneous information in the data, preprocessing is essential to refine the content. Once processed, the data is fed into a Long Short-Term Memory (LSTM) network to generate text vectors that encapsulate characteristics of American literature. Building on this, the Latent Dirichlet Allocation (LDA) topic model extracts salient features from these vectors. An illustrative analysis of American literature is conducted using these methods. Our findings indicate that a significant portion of novels, which mirror the societal life themes prevalent in the United States, aligned with the ideological currents of their time. Notably, these constituted a substantial majority—62.18%—of all American literary works during the period under review. This research not only facilitates the wider dissemination and exchange of American literary works but also contributes to elevating American literature to a new echelon of global recognition.

show abstract

“…Conducted a comprehensive review of prevalent approaches and tools for MSA, highlighting challenges and proposing recommendations, particularly for scarce resource languages. Additionally, [13] and [46] offer overviews of the field, yet they did not extensively explore the application of DL in MSA. In the past decade, cross-lingual sentiment classification has gained traction, particularly in resource-deficient languages.…”

Section: Introductionmentioning

confidence: 99%

Multilingual Sentiment Analysis Using Deep Learning: Survey

Bibi,

Ihsan,

Ashraf

et al. 2024

Preprint

0

View full text Add to dashboard Cite

The rise of the Internet has enabled people to express their opinions on various subjects through social media, blogs, and website comments. As a result, there has been a significant increase in research on sentiment analysis. However, most of the research efforts have focused on analyzing sentiment in English-language data, neglecting the wealth of information available in other languages. In this paper, we provide a comprehensive review of the current state-of-the-art in multilingual sentiment analysis. The survey investigates techniques for data preprocessing, representation learning, and feature extraction in multilingual sentiment analysis. It explores cross-lingual transfer learning, domain adaptation, and data augmentation methods that enhance the performance of sentiment analysis models, particularly in low-resource languages and domains. It provides insights into the state-of-the-art approaches, challenges, and opportunities in this evolving field and encourages further advancements in multilingual sentiment analysis research.

show abstract

Transfer learning and sentiment analysis of Bahraini dialects sequential text data using multilingual deep learning approach

Cited by 24 publications

References 24 publications

Multilingual Sentiment Analysis Using Deep Learning: Survey

Multilingual Sentiment Analysis Using Deep Learning: Survey

Exploring Themes and Patterns in American Literature Using Text Analysis Techniques

Multilingual Sentiment Analysis Using Deep Learning: Survey

Contact Info

Product

Resources

About