Top Research Papers on Sentiment Analysis

Sentiment analysis or opinion mining is the computational study of people’s opinions, appraisals, and emotions toward entities, events and their attributes in order to gather consumer opinions about its products and those of its competitors.

In the ever-expanding realm of the internet, where vast amounts of data are generated daily, platforms like Twitter become hubs for expressing opinions.This survey delves into sentiment analysis on Twitter, focusing on the challenges posed by unstructured, diverse opinions.Leveraging natural language processing (NLP) techniques, a robust sentiment analysis framework is constructed.The framework utilizes machine learning algorithms such as Naive Bayes, Maximum Entropy, and Support Vector Machine (SVM).A diverse dataset is collected, preprocessed, and used to train and evaluate the model.

This project focuses on applying sentiment analysis techniques to movie reviews, aiming to develop an efficient model for automatically classifying sentiments as positive, negative, or neutral, to create a robust sentiment analysis of accurately categorizing the sentiment conveyed in movie reviews.

A weak supervised neural model that aims at learning a set of sentiment clusters embedding from the sentence global representation of the target domain, and an attention-based LSTM model to address aspect-level sentiment analysis task based on the sentiment score retrieved from the proposed dictionary.

Sentiment Knowledge Enhanced Pre-training (SKEP) is introduced in order to learn a unified sentiment representation for multiple sentiment analysis tasks, and significantly outperforms strong pre-training baseline, and achieves new state-of-the-art results on most of the test datasets.

The study puts forth two key insights: relative efficacy of four sentiment analysis algorithms and undisputed superiority of pre-trained advanced supervised deep learning algorithm BERT in sentiment classification from text.

A danmaku sentiment dictionary is constructed and a new method using sentiment dictionary and Naïve Bayes for the sentiment analysis of dan maku reviews is presented, which has a significant effect on sentiment score and polarity detection.

The proposed method relies on a pre-trained language model and can capture the dependence on both targets and aspects for sentiment prediction and achieves a high performance in detecting target-aspect-sentiment triples even for the implicit target cases.

The extraction of tweets pertaining to the General Elections of India in 2019 is carried out along with the study of sentiments among Twitter users towards the major national political parties participating in the electoral process to prepare the classification model and compare it with the classical machine learning models.

A comprehensive exploration of LLMs’ proficiency in sentiment analysis, a core task in marketing research for understanding consumer emotions, opinions, and perceptions, finds that linguistic features such as the presence of lengthy, content-laden words improve classification performance, while other features such as single-sentence reviews and less structured social media text documents reduce performance.

The proposed approach based on a feature ensemble model related to tweets containing fuzzy sentiment by taking into account elements such as lexical, word-type, semantic, position, and sentiment polarity of words proves effective in improving the performance of tweet sentiment analysis in terms of the $F_{1}$ score.

This study proposes text classification with the use of bidirectional encoder representations from transformers (BERT) for natural language processing with other variants to improve accuracy rate, precision rate, recall rate, and F1-score.

This work explores an approach utilizing state-of-the-art machine translation technology and performs sentiment analysis on the English translation of a foreign language text and indicates that entity sentiment scores obtained by the method are statistically significantly correlated across nine languages of news sources and five languages of a parallel corpus.

This article uses SenticNet to extract natural language concepts and fine-tune several feature types on a subset of MuSe-CAR to explore the content of a video as well as learning to predict emotional valence, arousal, and speaker topic classes.

According to this analysis, LSTM and CNN algorithms are the most used deep learning algorithms for sentiment analysis.

Text mining implementation in seafarers’ medical documents can generate better knowledge of medical issues that often happened onboard to improve quality of healthcare, the possibility of fewer medical errors, and low costs.

The hybrid models increased the accuracy for sentiment analysis compared with single models on all types of datasets, especially the combination of deep learning models with SVM, and the reliability of the latter was significantly higher.

An overview of the method for completing this task as well as the applications of sentiment analysis is discussed, which evaluates, compares, and investigates the approaches used to gain a comprehensive understanding of their advantages and disadvantages.

This cutting-edge book brings together experts in the field to provide a multidimensional perspective on sentiment analysis, covering both foundational and advanced methodologies. Readers will gain insights into the latest natural language processing and machine learning techniques that power sentiment analysis, enabling the extraction of nuanced emotions from text. Key Features: •State-of-the-Art Techniques: Explore the most recent advancements in sentiment analysis, from deep learning approaches to sentiment lexicons and beyond. •Real-World Applications: Dive into a wide range of application...

This work does sentiment analysis on text reviews by using Long Short-Term Memory (LSTM), and recently, thanks to their ability to handle large amounts of knowledge, neural networks have achieved a good success on sentiment classification.