Multilingual Sentiment Analysis: A Systematic Literature Review

As the e-commerce platforms grew exponentially, the volume of multilingual customer reviews increased, indicating that sentiment analysis is a priceless tool for finding consumer sentiment, enhancing marketing strategies, and improving customer experience. Nevertheless, emotion classification in multilingual reviews is very hard, and for one causes the variability of the language, the ambiguity of the sentiment, hierarchical word dependencies, and class imbalance, which can skew traditional models. In order to resolve such challenges, this paper introduces a T5-CapsNet ensemble model, which combines the T5 transformer for context-embedded feature extraction with Capsule Networks (CapsNet) for hierarchical sentiment learning. Furthermore, the model is further enhanced by a GAN-based data augmentation technique, which increases the number of minority class reviews in a dataset by adding synthetic minority class reviews in an effort to correct dataset imbalance and promote classification fairness. As an ensemble fusion strategy, weighted voting and stacking ensemble learning are used to improve sentiment prediction by making good use of the advantages of T5 and CapsNet. Experimental evaluations on the Multilingual Amazon Reviews Corpus (MARC) confirm that the proposed model surpasses the best sentiment classifier to reach an accuracy of 97.56%. It turns out that this hybrid deep learning approach very well captures the complex sentiment structures, or to put it differently, the multilingual e-commerce sentiment analysis largely benefited from such a hybrid deep learning approach. The findings from this study will be a foundation for building more advanced emotion classification models that can assist in improving customer sentiment analysis, automated feedback systems, as well as decision-making in global e-commerce ecosystems.

This chapter discusses the concept of natural language processing (NLP), specifically how the NLP is applied. The chapter further outlines the typical functions of the NLP. In addition, it explores the NLP in strategy and strategy implementation.The NLP is a branch of computer science, AI and linguistics that focuses on the interaction between computer programs and human language. There are three functions of the NLP, namely, machine translation (MT), text summarisation and sentiment analysis (SA). MT is a branch of computer linguistics that analyses the use of computerised tools to translate the context derived from this, from one language to the next. The language that is being translated is the human language.Automatic text summarisation refers to a process of bringing about a succinct and meaningful summary of the text. SA is a way of finding out the polarity or strength of the opinion that is expressed in written text. The opinion could be either positive or negative. MT has three major approaches, namely, rule-based MT, statistical MT and neural MT. A rule-based system would typically require the expert to know both the source and the target languages. This knowledge is then used to develop syntactic, semantic and morphological rules to achieve the translation. The statistical approach uses statistical models based on the analysis of bilingual text corpora. The neural MT approach uses neural networks to achieve machine translation. There are two broad categories of text summarisation approaches, namely, extractive summarisation and abstractive summarisation. Furthermore, there are four popular types of SA, namely, the fine-grained SA, emotion detection, aspect-based SA and multilingual SA. The firm that deploys the NLP and ML in Big Data Analytics would gain crucial and better insights, setting the firm apart from its competitors.

Opinionated texts are widely available as the use of e-commerce platforms has become more popular around the world. Sentiment Analysis is the field of study which aims to understand users’ preferences and opinions, extracting useful knowledge from this kind of data. Despite advances in the last years, some topics remain unexplored. This is the case of multilingual aspect-based sentiment analysis (MABSA), which aims to process reviews written in multiple languages. In this work, we propose EurOpi, a MABSA technique that relies on a knowledge base, i.e., a multilingual product catalog, to map the aspects evaluated by users from opinionated texts into product attributes. We show that (i) EurOpi effectively maps aspects to catalog attributes, and (ii) a multilingual product catalog enriched with opinions makes it easy to compare opinions across different languages. Finally, we release a dataset, containing reviews in English, Spanish, and Italian annotated at the aspect level to help increment research on MABSA.

Opinions are ubiquitous in text, and readers of online text—from consumers to sports fans to news addicts to governments—can benefit from automatic methods that synthesize useful opinion-oriented information from the sea of data. In this chapter on opinion mining and sentiment analysis, we introduce an idealized, end-to-end opinion analysis system and describe its components. We present methods for classifying documents and text passages according to their sentiment as well as methods that perform more fine-grained extraction of opinion expressions, their holders and their targets. We also address supplementary tasks of opinion lexicon construction, opinion summarization, opinion-oriented question answering, multi-lingual sentiment analysis and compositional approaches to phrase-level sentiment analysis.

In this study, corpus-assisted sentiment analysis is used to explore how news headlines frame the Palestine–Israel conflict by analyzing a dataset consisting of 5000 news headlines retrieved from Google News. The sentiment of headlines was classified as positive, negative, or neutral, using a supervised machine learning approach of logistic regression. The sentiment analysis results reveal a dominance of neutral sentiment, with considerable positive sentiment, which is indicative of the resolution-centered framing employed by the media outlets. The study adopts the Media Framing theory and Social Identity theory to establish how media framing impacts public perception and reinforces social identity-based bias. The results highlight the importance of better balanced and solution-oriented reporting in support of conflict resolution efforts. However, the strong presence of negative sentiment, on the contrary, is indicative of media outlets' conflict-oriented framing. Sentiment analysis could be used as a useful tool for policymakers, journalists, and researchers to gauge the effect of media storytelling on public opinion. For future research, multilingual and longitudinal sentiment analysis can be extended to analyze the changing media discourses in a different cultural context.

Sentiment analysis is an important task in natural language processing. Twitter sentiment analysis (SA) is the most frequently researched discipline today. Only a few researchers have concentrated on multilingual twitter sentiment analysis, while the majority of scholars have worked on English twitter sentiment analysis. Recently, there seems to be a large increase in the quantity of data sets transmitted via social media in a variety of languages. This work examines the semantic nature of a text in order to classify positive and negative tweets using Hindi and Kannada language models, respectively. Machine learning models such as Naïve Bayes Classifier, KNeighbors’ Classifier, Decision Tree Classifier and Random Forest Classifier are used to tackle the classification task.

Due to the rapid growth of digital news outlets and the way the public perceives information and news, increasingly being shaped by online content. Our research intends to conduct a sentiment analysis of news articles in Hindi and English, to analyze and examine the trends in public sentiment across different sectors, namely - finance, healthcare and education. We utilize MuRIL, mBERT, and VADER for sentiment classification, ensuring support for multiple languages and contextual precision. Furthermore, we incorporate fake news detection using Random Forest, Logistic Regression, and XGBoost, which helps improve the dependability of insights gathered from news sources. The dataset was crafted through scraping and labeling of news articles via automation. We also fine tuned transformer-based models for the purpose of sentiment analysis and classification. To evaluate the model performance, hyperparameters were optimized such as learning rate, batch size, number of epochs as well as analyzing the train-test split. The findings concluded that mBERT performs the best in multilingual sentiment analysis, having high accuracy due to the robust contextual comprehension.

Natural language processing (NLP) is being widely used globally for a variety of value-creation tasks ranging from chat-bots and machine translations to sentiment and topic analysis and multilingual large language models (LLMs). However, most of the advances are initially implemented within the English language framework, and it takes time and resources to develop comparable resources in other languages. The advances in machine translations have enabled the rapid and effective conversion of content in global languages into English and vice-versa. This creates potential opportunities to apply English language NLP methods and tools to other languages via machine translations. However, although this idea is powerful, it needs to be validated and processes and best practices need to be developed and kept updated. The present research is an effort to contribute to the development of best practices and an evaluation framework. We present a systematic and repeatable state-of-the-art process to evaluate the viability of applying English language sentiment analysis tools to Italian text by using multiple English language machine translation mechanisms such that it can be easily extended to other languages.

Social networking sites and micro blogs provide tremendous amount of real time data every day. Sentiment analysis or opinion mining aims to automate the process of sentiment extraction from the user content available online. Twitter in recent years due to its high subscriber rate and diverse audience, has become increasingly powerful in representing and changing user opinions over an object or event. This paper focuses on research conducted within the field of twitter sentiment analysis. The objective is to comprehensively investigate the task of sentiment analysis and its sub processes and identify the different tools, techniques or other resources used or applied on twitter data during the process. A Systematic Literature Review (SLR) has been conducted to identify 40 researches, relevant to sentiment identification and analysis. The work presented covers major tools and techniques used during sentiment mining process and maybe utilized by researchers or practitioners for identifying potential research directions as well as suggest possible software development areas that need to be explored.

This study investigates the trends and challenges in information science with a special focus on political tweets. The past decade has witnessed a transformation in information mining, extraction and production using algorithms on social media platforms. The unique data structure of Twitter has gained scholarly attention for its intelligence to produce voluminous information which is convenient and rapid. But the efficiency of Twitter as a platform to obtain political knowledge remains a question. Various socio-technological research methods have emerged making Twitter an integrated topic of study for scholars from media studies, computer science and information science. The big data environment provides hashtags, @-mentions, and various digital affordances necessitating its study to be an integral part of social science research. Thus, the systematic literature review aims to examine tweeting patterns of political leaders to study variables such as ideology diffusion, polarization, political issues, digital campaigns etc. The study also examines computational research methods to retrieve Twitter data pertaining to political information. Academic investigation consists of approaches to automated data collection on Twitter, pre-processing techniques using R and Python, machine learning procedures and sentiment analysis used on Twitter data. The study showcases India’s stand in adopting the niche socio-technological methods in social science research.

The resource constraints in many languages have made the multi-lingual sentiment analysis approach a viable alternative for sentiment classification. Although a good amount of research has been conducted using a multi-lingual approach in languages like Chinese, Italian, Romanian, etc. very limited research has been done in Bengali. This paper presents a bilingual approach to sentiment analysis by comparing machine translated Bengali corpus to its original form. We apply multiple machine learning algorithms: Logistic Regression (LR), Ridge Regression (RR), Support Vector Machine (SVM), Random Forest (RF), Extra Randomized Trees (ET) and Long Short-Term Memory (LSTM) to a collection of Bengali corpus and corresponding machine translated English version. The results suggest that using machine translation improves classifiers performance in both datasets. Moreover, the results show that the unigram model performs better than higher-order n-gram model in both datasets due to linguistic variations and presence of misspelled words results from complex typing system of Bengali language; sparseness and noise in the machine translated data, and because of small datasets.

Sentiment Analysis (SA) examines the hassle of studying texts, like posts and reviews, uploaded by way of customers on microblogging platforms, forums, and electronic agencies, concerning the evaluations they have got about a product, service, event, man or woman or idea. The common used of SA is classifying text to a several class such as positive, neutral and negative term classification. This paper aims to compare the techniques being used to examine SA especially for reviewing product or services. These techniques are not only being applied in review product prediction, but they were applied in different filed such as production, sales and marketing. Based on the comparison of each model and their uses, lexicon-based approach is the best solution for classifying SA.

An essential function of natural language processing is sentiment analysis. Which holds substantial significance in understanding public opinion across diverse domains. However, while sentiment analysis methodologies abound in English, there exists a notable scarcity of research addressing sentiment analysis in languages like Hindi. In response, the above paper provides a pioneering aspect to Hindi sentiment analysis through the development of a hybrid deep learning-machine learning model integrated with a metaheuristic optimization algorithm. By amalgamating the strengths for normal machine learning (ML) techniques and deep learning (DL), this model endeavours to boost accuracy and robustness in sentiment classification tasks specific to Hindi text. Furthermore, the inclusion of a metaheuristic optimization algorithm aims to optimize crucial model parameters, thereby improving convergence speed and overall performance. The proposed approach is motivated by the need for more comprehensive sentiment analysis techniques tailored for multilingual social media data, particularly in languages like Hindi, which are prevalent on various online platforms. Through empirical evaluation and comparative analysis, this paper demonstrates the efficacy and potential applications of the proposed hybrid model in real-world sentiment analysis scenarios. This research contributes to bridging the gap in sentiment analysis research for non-English languages and lays the foundation for further advancements in multilingual sentiment analysis methodologies.

We introduce Big Data Analytics (BDA) and Sentiment Analysis (SA) to the study of international negotiations, through an application to the case of the UK-EU Brexit negotiations and the use of Twitter user sentiment. We show that SA of tweets has potential as a real-time barometer of public sentiment towards negotiating outcomes to inform government decision-making. Despite the increasing need for information on collective preferences regarding possible negotiating outcomes, negotiators have been slow to capitalise on BDA. Through SA on a corpus of 13,018,367 tweets on defined Brexit hashtags, we illustrate how SA can provide a platform for decision-makers engaged in international negotiations to grasp collective preferences. We show that BDA and SA can enhance decision-making and strategy in public policy and negotiation contexts of the magnitude of Brexit. Our findings indicate that the preferred or least preferred Brexit outcomes could have been inferred by the emotions expressed by Twitter users. We argue that BDA can be a mechanism to map the different options available to decision-makers and bring insights to and inform their decision-making. Our work, thereby, proposes SA as part of the international negotiation toolbox to remedy for the existing informational gap between decision makers and citizens’ preferred outcomes.

The sentiment analysis process that gives this work its name is the main theme of the work. Since the beginning of 2000, sentiment analysis has become one of the most active research areas by researchers working on natural language processing and social networking analysis. In addition, data mining, web mining, and text mining are also studied extensively. Moreover, the method of sentiment analysis has spread over many fields, from computer science to management science, from social science to economics, due to the importance given to the business world as a whole and the collectivity. In this study, Konstanz Information Miner (KNIME), which is a powerful data mining tool with its richest features and many visualization tools, was used on twitter data. Ten thousand Twitter data were used in this study. The sentiment analysis study, which is in fact a classification study, was conducted using machine learning algorithms on Twitter data. The results of the study were interpreted by carrying out an accuracy analysis. It is anticipated that the use of the KNIME, which has rich visualization tools, will be widespread in sentiment analysis studies to make these works both easier and more reliable.