Opinion Extraction Research Articles

Exploring the E-learning Supporting Systems for Students with Special Needs

Objectives: This study provided a comprehensive exposition of an educational delivery service framework incorporating inclusive education for children with special needs. It is of the utmost importance to investigate the most efficient models that can be established to assist children who have special needs in becoming active members of the society. The field of e-learning has experienced significant expansion owing to the proliferation of a diverse range of technological tools and devices which enable users to access educational resources. Numerous educational support frameworks have been implemented to make the integration of learners with special needs into regular academic programs swifter.
 
 Methodology: This study used the literature review as its methodology. The study gathered data from articles, books, videos and official circulations about the services and supporting systems used for students with special needs in Saudi Arabia. The study also relied on the descriptive approach to support the review by conducting interviews with school headmasters in 20 different schools. The interviews were content-analysed and reviewed to extract opinions on the models used in these schools.
 
 Results and conclusion: Most of the interviewed participants agreed that the comprehensive quality model presents better opportunities for all students and teachers alike. The findings showed the availability of several models that educators can use to evaluate the e-learning supporting systems. The study benefits teachers and educators in understanding the e-learning supporting systems.

A More Fine-Grained Aspect–Sentiment–Opinion Triplet Extraction Task

Sentiment analysis aims to systematically study affective states and subjective information in digital text through computational methods. Aspect Sentiment Triplet Extraction (ASTE), a subtask of sentiment analysis, aims to extract aspect term, sentiment and opinion term triplets from sentences. However, some ASTE’s extracted triplets are not self-contained, as they reflect the sentence’s sentiment toward the aspect term, not the sentiment between the aspect and opinion terms. These triplets are not only unhelpful to people, but can also be detrimental to downstream tasks. In this paper, we introduce a more nuanced task, Aspect–Sentiment–Opinion Triplet Extraction (ASOTE), which also extracts aspect term, sentiment and opinion term triplets. However, the sentiment in a triplet extracted with ASOTE is the sentiment of the aspect term and opinion term pair. We build four datasets for ASOTE. A Position-aware BERT-based Framework (PBF) is proposed to address ASOTE. PBF first extracts aspect terms from sentences. For each extracted aspect term, PBF generates an aspect term-specific sentence representation, considering the aspect term’s position. It then extracts associated opinion terms and predicts the sentiments of the aspect–opinion term pairs based on the representation. In the experiments on the four datasets, PBF has set a benchmark performance on the novel ASOTE task.

Identifying Reproductive Behavior Arguments in Social Media Content Users’ Opinions through Natural Language Processing Techniques

Big data provides researchers with valuable sources of information for studying demographic behavior in the population. One such source is the texts posted by social network users on various demographic issues. This study utilizes methods for automatically extracting user opinions from the “VKontakte” social network. The extracted texts are then classified using the Conversational RuBERT neural network model to investigate opinions related to reproductive behavior in the population. The classification process addresses two consecutive problems. Firstly, it aims to identify whether a user’s comment contains argumentation. Secondly, if an argument is present, it seeks to determine its type within the context of the “personal-public” dichotomy. To search for arguments and classify their types, six experiments were conducted, varying the dataset and the number of classes. The method employed for automatic extraction and classification of user opinions on the “VKontakte” social network has demonstrated the ability to accurately classify users’ comments, identifying the presence of argumentation and categorizing the arguments within the “personal-public” dichotomy. This enables the identification of personal and social attitudes, values, stories, and opinions, thus facilitating the study of reproductive behavior.

A Machine-Learning-Inspired Opinion Extraction Mechanism for Classifying Customer Reviews on Social Media

Machine learning frameworks categorizing customer reviews on online products have significantly improved sales and product quality for major manufacturers. Manually scrutinizing extensive customer reviews is imprecise and time-consuming. Current product research techniques rely on text mining, neglecting audio, and image components, resulting in less productive outcomes for researchers and developers. AI-based machine learning frameworks that consider social media and online buyer reviews are essential for accurate recommendations in online e-commerce shops. This research paper proposes a novel machine-learning-based framework for categorizing customer reviews that uses a bag-of-features approach for feature extraction and a hybrid DNN framework for robust classification. We assess the performance of our machine learning framework using AliExpress and Amazon e-commerce product review data provided by customers, and we have achieved a classification accuracy of 91.5% with only 8.46% fallout. Moreover, when compared with state-of-the-art models, our proposed model shows superior performance in terms of sensitivity, specificity, precision, fallout, and accuracy.

A survey on Relation Extraction

With the advent of the Internet, the daily production of digital text in the form of social media, emails, blogs, news items, books, research papers, and Q&A forums has increased significantly. This unstructured or semi-structured text contains a huge amount of information. Information Extraction (IE) can extract meaningful information from text sources and present it in a structured format. The sub-tasks of IE include Named Entity Recognition (NER), Event Extraction, Relation Extraction (RE), Sentiment Extraction, Opinion Extraction, Terminology Extraction, Reference Extraction, and so on.One way to represent information in the text is in the form of entities and relations representing links between entities. The Entity Extraction task identifies entities from the text, and the Relation Extraction (RE) task can identify relationships between those entities. Many NLP applications can benefit from relational information derived from natural language, including Structured Search, Knowledge Base (KB) population, Information Retrieval, Question-Answering, Language Understanding, Ontology Learning, etc. This survey covers (1) basic concepts of Relation Extraction; (2) various Relation Extraction methodologies; (3) Deep Learning techniques for Relation Extraction; and (4) different datasets that can be used to evaluate the RE system.

TWITTER SENTIMENT ANALYSIS

Sentiment analysis is a popular research field that aims to extract opinions, attitudes, and emotions from social media platforms like Twitter. Traditionally, sentiment analysis has focused on analyzing textual data. Twitter, being a well-known microblogging platform where users post updates in the form of tweets, is often used as a data source for sentiment analysis studies. In this particular paper, the authors utilize a publicly available labeled dataset from Kaggle. They also propose a set of preprocessing steps to enhance the manageability of tweets for natural language processing techniques. Since the dataset consists of pairs of tweets and their corresponding sentiment labels, supervised machine learning is employed. The authors propose sentiment analysis models based on naive Bayes, logistic regression, and support vector machine algorithms with the objective of achieving more effective sentiment analysis. In Twitter sentiment analysis, tweets are typically categorized into positive or negative sentiment. Machine learning classifiers can be utilized for this purpose. These classifiers can be valuable for various entities such as businesses, political parties, and analysts, as they can evaluate the sentiments expressed towards them. By appropriately training the machine learning models with labeled data, tweets can be accurately classified without the need for a predefined word database. Consequently, machine learning techniques offer a superior and faster approach to performing sentiment analysis. Keywords: Twitter; sentiment; Web data; text mining; SVM; Bayesian algorithm; hybrid; ensembles

Adaptive Particle Grey Wolf Optimizer with Deep Learning-based Sentiment Analysis on Online Product Reviews

The increasing use of e-commerce websites and social networks is continually generating an immense amount of data in various forms, such as text, images or sounds, videos, etc. Sentiment analysis (SA) in online product reviews is a method of identifying the overall sentiment of customers about a specific product or service. This study used Natural Language Processing (NLP) and Machine Learning (ML) algorithms to identify and extract opinions and emotions expressed in text. Online reviews are often written in informal language, slang, and dialects, making it difficult for ML models to accurately classify sentiments. In addition, the use of misspelled words or incorrect grammar can further complicate the analysis. The recent developments of Deep Learning (DL) models can be used for the accurate classification of sentiments. This paper presents an Adaptive Particle Grey Wolf Optimizer with Deep Learning Based Sentiment Analysis (APGWO-DLSA) method to accurately classify sentiments in product reviews. Initially, data pre-processing was performed to improve the quality of the product reviews using the word2vec embedding process. For sentiment classification, the proposed method used a Deep Belief Network (DBN) model. Finally, the hyperparameter tuning of the DBN was performed using the APGWO algorithm. An extensive experimental analysis demonstrated the improved results of APGWO-DLSA over other methods, showing a maximum accuracy of 94.77% and 85.31% on the Cell Phones And Accessories (CPAA) and Amazon Products (AP) datasets.

Towards Generalization of Machine Learning Models: A Case Study of Arabic Sentiment Analysis

The abundance of social media data in the Arab world, specifically on Twitter, enabled companies and entities to exploit such rich and beneficial data that could be mined and used to extract important information, including sentiments and opinions of people towards a topic or a merchandise. However, with this plenitude comes the issue of producing models that are able to deliver consistent outcomes when tested within various contexts. Although model generalization has been thoroughly investigated in many fields, it has not been heavily investigated in the Arabic context. To address this gap, we investigate the generalization of models and data in Arabic with application to sentiment analysis, by performing a battery of experiments and building different models that are tested on five independent test sets to understand their performance when presented with unseen data. In doing so, we detail different techniques that improve the generalization of machine learning models in Arabic sentiment analysis, and share a large versatile dataset consisting of approximately 1.64M Arabic tweets and their corresponding sentiment to be used for future research. Our experiments concluded that the most consistent model is trained using a dataset labelled by a cascaded approach of two models, one that labels neutral tweets and another that identifies positive/negative tweets based on the Arabic emoji lexicon after class balancing. Both the BERT and the SVM models trained using the refined data achieve an average F-1 score of 0.62 and 0.60, and standard deviation of 0.06 and 0.04 respectively, when evaluated on five diverse test sets, outperforming other models by at least 17% relative gain in F-1. Based on our experiments, we share recommendations to improve model generalization for classification tasks.

Has COVID-19 Changed Consumers’ Satisfiers and Dissatisfiers? Evidence from Online Reviews of 5-Star Hotels in Shanghai and Beijing

ABSTRACT Many studies have analyzed the asymmetric relationship between hotel service quality attributes and satisfaction, and tried to find consumers’ satisfiers and dissatisfiers, aiming at enhancing satisfaction more efficiently. However, the impact of COVID-19 has led to changes in consumers’ expectations for hotel services, and the above findings might face invalidation. To date, we are still unknown whether consumers’ satisfiers/dissatisfiers changed. This study fills this research gap by mining online reviews of five-star hotels from Shanghai and Beijing before and during the pandemic. The results found that the asymmetric categories of Sleep quality and Internet/Wi-Fi attributes have changed. Specifically, Sleep quality and Internet/Wi-Fi became dissatisfiers from hybrids, indicating that hoteliers only need to maintain their normal performance, and do not invest too many resources because they bring no satisfaction; attributes like Room, decoration, etc. remain hybrids. Additionally, we performed opinion extraction for the dissatisfier attributes to further understand what causes consumer dissatisfaction. The results contribute to the literature by shedding light on the pandemic’s impacts on the asymmetric effects of service quality attributes. The cause analysis can help hoteliers develop specific measures to mitigate the adverse effects of COVID-19.

Independent component support vector regressive deep learning for sentiment classification

Sentiment analysis is the process used to extract the keywords from the user review and classify the text into positive, negative and neutral. Sentiment analysis and opinion mining is the field used to analyzes people opinion, sentiment, evaluation, attitude and emotion. Many researchers introduced opinion mining methods to improve the detection accuracy. But, the time consumption was not reduced and accuracy level was not improved. In order to address these problems, an Independent Component Support Vector Regressive Deep Learnt Sentiment Classification (ICSD) Method is designed. ICSD Method comprises five layers to perform sentiment classification. ICSD Method performs pre-processing, feature extraction and classification to enhance the classification accuracy with extracted words from user review comments. Initially in ICSD Method, the user review comments are collected as an input at the input layer. The user review comments are sent to the hidden layer 1. In that layer, ICSD Method pre-processes the use review comments for removing the stop words to reduce the file size. The pre-processed user review comments are sent to the hidden layer 2. In hidden layer 2, Independent Component Feature Extraction is carried out in ICSD Technique to extract the opinion word from review comments. The associated opinion words are arranged for the semantic similarity of sentiment based on the extracted word to minimize the time consumption. After that, the extracted words are transferred to the hidden layer 3. In that layer, Support Vector Regressive Sentiment Classification is performed in ICSD Method to examine the semantic opinion words for determining the sentiment class label. The sentiment class are categorized into positive, neutral and negative sentiments. Finally, the results are sent to the output layer. This in turn helps to minimize the time consumption and to progress the accuracy of opinion mining. The performance evaluation of ICSD Method is carried out with consumer product and services reviews extracted. The parameters used are evaluated with number of customer review words, accuracy, time complexity and false positive rate. Experimental evaluation of ICSD Method minimizes the time consumption and false positive rate during opinion extraction from reviewers.

Intelligent Machine Learning with Metaheuristics Based Sentiment Analysis and Classification

Sentiment Analysis (SA) is one of the subfields in Natural Language Processing (NLP) which focuses on identification and extraction of opinions that exist in the text provided across reviews, social media, blogs, news, and so on. SA has the ability to handle the drastically-increasing unstructured text by transforming them into structured data with the help of NLP and open source tools. The current research work designs a novel Modified Red Deer Algorithm (MRDA) Extreme Learning Machine Sparse Autoencoder (ELMSAE) model for SA and classification. The proposed MRDA-ELMSAE technique initially performs preprocessing to transform the data into a compatible format. Moreover, TF-IDF vectorizer is employed in the extraction of features while ELMSAE model is applied in the classification of sentiments. Furthermore, optimal parameter tuning is done for ELMSAE model using MRDA technique. A wide range of simulation analyses was carried out and results from comparative analysis establish the enhanced efficiency of MRDA-ELMSAE technique against other recent techniques.

The Sentiment Analysis of EndSARS Protest in Nigeria

The extraction of public opinions from online communication platforms can serve several purposes in corporate institutions, state politics, and governance. The analysis of these opinions may be useful for both immediate business decision making and professional planning. This analysis is becoming relevant in managing social movements and digital activism by applying computational technology. There is a need to deploy this opinion mining technology to the recent largest digital activism in Nigeria known as the #EndSARS movement. In this work, we proposed the EndSARS live analytics framework which holds a promising solution to social unrest and may serve as a panacea to curbing the menace of vandalism resulting from unresolved protest issues. Using a dataset of 12,357 tweets, we demonstrated that computational technology can be relevant to addressing online protests. The result of the analysis shows the eight basic emotions expressed during the protest and approaches the government may adopt to address future activisms.

SpanMTL: a span-based multi-table labeling for aspect-oriented fine-grained opinion extraction

Aspect-oriented Fine-grained Opinion Extraction (AFOE) aims to extract the aspect terms, corresponding opinion terms and sentiment polarity in a target sentence. Most previous methods treat AFOE as word-level or span-level task, which ignore the complementarity of these two tasks. To integrate the merits of word-level and span-level information, we construct an end-to-end Span-based Multi-Table Labeling (SpanMTL) framework. SpanMTL combines word-based and span-based table labeling to tackle AFOE task. Specifically, in the proposed model, we use two separate BiLSTMs to encode the information of aspect and opinion terms into a word-based 2D representation table. Based on the table, we construct span-based table with CNN by associating the word-pair representations. At last, we integrate the table label distributions of word- and span-based table labeling to generate a multi-table labeling. The proposed method improves the performances of Opinion Pair Extraction (OPE) and Opinion Triplet Extraction (OTE) tasks by introducing span information, especially on the datasets with lots of spans. We have conducted various experiments on AFOE datasets to validate our method. The experimental results show that our method outperforms other baselines when the sentences having lots of span information.

Restructuring and Reshaping Africa Oil Exporting Countries Post COVID-19 – A Participatory Development Strategy Approach

Abstract Research Background: The COVID-19 pandemic has the capacity of severely disrupting economic activities and triggering economic crisis, especially in Africa’s Oil Exporting Countries (AOECs). The African economy is likely to be the worst hit, especially the Africa Oil Exporting Countries (AOECs), as they have been majorly low income countries and considering the fall in oil prices, as oil revenue forms a major source of their revenue and government expenditure. Purpose: This study explored the stakeholders’ opinions on reshaping and restructuring the economies of six African Oil Exporting Countries, with the aim of ascertaining the views of academics within the six AOECs, as regards the economic revival post COVID-19. Research methodology: The study utilized the Participatory Development Strategy Approach (PDSA), employing the Cronbach Alpha Reliability test, Estimated Response Rate (ERR) and Explanatory Factor Analysis (EFA) to extract opinions from 1,260 stakeholders within the six AOECs. Results: The results show that the stakeholders are of the opinion that the solutions to the rebuilding of AOECs are multi-faceted, suggesting a mixture of both government and private institutions in varying degrees. Some of the respondents favoured going back to agriculture and agribusiness to revamp their economies. Novelty: The study utilized an uncommon methodology; the Participatory Development Strategy Approach (PDSA) to achieve its objective. The PDSA is meant to allow the affected stakeholders’ participation in the policy making process. The respondents were purely academics, as it is believed that academics are the sources of hope of solving myriads of human challenges such as hunger and economic crisis.

AsU-OSum: Aspect-augmented unsupervised opinion summarization

Opinion summarization can facilitate user’s decision-making by mining the salient review information. However, due to the lack of sufficient annotated data, most of the early works are based on extractive methods, which restricts the performance of opinion summarization. In this work, we aim to improve the informativeness of opinion summarization to provide better guidance to users. We consider the setting with only reviews without corresponding summaries, and propose an aspect-augmented model for unsupervised abstractive opinion summarization, denoted as AsU-OSum. We first employ an aspect-based sentiment analysis system to extract opinion phrases from reviews. Then, we construct a heterogeneous graph consisting of reviews and opinion clusters as nodes, which is used to enhance the Transformer-based encoder–decoder framework. Furthermore, we design a novel cascaded attention mechanism to prompt the decoder to pay more attention to the aspects that are more likely to appear in summary. During training, we introduce a sentiment accuracy reward that further enhances the learning ability of our model. We conduct comprehensive experiments on the Yelp, Amazon, and Rotten Tomatoes datasets. Automatic evaluation results show that our model is competitive and performs better than the state-of-the-art (SOTA) models on some ROUGE metrics. Human evaluation results further verify that our model can generate more informative summaries and reduce redundancy.

Comparative Analysis of Deep Learning Approaches for Twitter Text Classification

Abstract—Sentiment analysis (also known as opinion mining or emotion AI) is the use of natural language processing, text analysis, computational linguistics, and biometrics to systematically identify, extract, quantify, and study affective states and subjective information. Sentiment analysis is widely applied to voice of the customer materials such as reviews and survey responses, online and social media, and healthcare materials for applications that range from marketing to customer service to clinical medicine. With the rise of deep language models, such as RoBERTa, also more difficult data domains can be analyzed, e.g., news texts where authors typically express their opinion/sentiment less explicitly. Sentiment analysis aims to extract opinion automatically from data and classify them as positive and negative. Twitter widely used social media tools, been seen as an important source of information for acquiring people’s attitudes, emotions, views, and feedbacks. Within this context, Twitter sentiment analysis techniques were developed to decide whether textual tweets express a positive or negative opinion. In contrast to lower classification performance of traditional algorithms, deep learning models, including Convolution Neural Network (CNN) and Bidirectional Long Short-Term Memory (Bi-LSTM), have achieved a significant result in sentiment analysis. Keras is a Deep Learning (DL) framework that provides an embedding layer to produce the vector representation of words present in the document. The objective of this work is to analyze the performance of deep learning models namely Convolutional Neural Network (CNN), Simple Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM), bidirectional Long Short-Term Memory (Bi-LSTM), BERT and RoBERTa for classifying the twitter reviews. From the experiments conducted, it is found that RoBERTa model performs better than CNN and simple RNN for sentiment classification. Keywords—Convolution Neural Network (CNN), Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Deep Learning, Bidirectional Long Short-Term Memory (BiLSTM), Bidirectional Encoder Representations from Transformers (BERT), Robustly Optimized BERT Pre-training Approach (RoBERTa).

OpExHAN: opinion extraction using hierarchical attention network from unstructured reviews.

In recent decades, sellers and merchants have asked their customers to share their opinion on the products at online marketplace. Analysis of the massive amounts of reviews for a potential customer is an immense challenge, to decide whether to purchase a product or not. In this paper, a hierarchical attention network-based framework is presented to resolve this challenge. In this proposed framework, the Amazon’s Smartphone review dataset is preprocessed using NLP approaches and then applied Glove embedding to extract word vector representation of reviews which identifies contextual information of words. These word vectors are fed into the hierarchical attention network, which produces vectors at the word and sentence levels. Bi-GRU model encodes the words and sentences into hidden vectors. Finally, reviews are classified into five opinion classes like extremely positive, positive, extremely negative, negative and neutral. Furthermore, to perform the experiments with the proposed method, the dataset is divided into three parts such as 80% train, 10% validation and 10% test. Experiments reveal that the proposed framework outperforms baseline methods in terms of accuracy, precision and recall. The OpExHAN model achieved admirable results like 94.6% accuracy, 91% both precision and recall after a lot of hyper-parameter experimentation.

Opinion Mining Using Enriched Joint Sentiment-Topic Model

Sentiment analysis has the potential to significantly impact several fields, such as trade, politics, and opinion extraction. Topic modeling is an intriguing concept used in emotion detection. Latent Dirichlet Allocation is an important algorithm in this subject. It investigates the semantic associations between terms in a text document and takes into account the influence of a subject on a word. Joint Sentiment-Topic model is a framework based on Latent Dirichlet Allocation method that investigates the influence of subjects and emotions on words. The emotion parameter is insufficient, and additional factors may be valuable in performance enhancement. This study presents two novel topic models that extend and improve Joint Sentiment-Topic model through a new parameter (the author’s view). The proposed methods care about the author’s inherent characteristics, which is the most important factor in writing a comment. The proposed models consider the effect of the author’s view on words in a text document. The author’s view means that the author creates an opinion in his mind about a product/thing before selecting the words for expressing the opinion. The new parameter has an immense effect on model accuracy regarding evaluation results. The first proposed method is author’s View-based Joint Sentiment-Topic model for Multi-domain. According to the evaluation results, the highest accuracy value in the first method is equal to 85%. It also has a lower perplexity value than other methods. The second proposed method is Author’s View-based Joint Sentiment-Topic model for Single-domain. According to the evaluation results, it achieves the highest accuracy with 95%. The proposed methods perform better than baseline methods with different topic number settings, especially the second method with 95% accuracy. The second method is a version of the first one, which outperforms baseline methods in terms of accuracy. These results demonstrate that the parameter of the author’s view improves sentiment classification at the document level. While not requiring labeled data, the proposed methods are more accurate than discriminative models such as Support Vector Machine (SVM) and logistic regression, based on the evaluation section’s outcomes. The proposed methods are simple with a low number of parameters. While providing a broad perception of connections between different words in documents of a single collection (single-domain) or multiple collections (multi-domain), the proposed methods have prepared solutions for two different situations (single-domain and multi-domain). The first proposed method is suitable for multi-domain datasets, but the second proposed method is suitable for single-domain datasets. While detecting emotion at the document level, the proposed models improve evaluation results compared to the baseline models. Eight datasets with different sizes have been used in implementations. For evaluations, this study uses sentiment analysis at the document level, perplexity, and topic coherency. Also, to see if the outcomes of the suggested models are statistically different from those of other algorithms, the Friedman test, a statistical analysis, is employed.

Double embedding and bidirectional sentiment dependence detector for aspect sentiment triplet extraction

Aspect sentiment triplet extraction (ASTE) is a popular subtask related to aspect-based sentiment analysis (ABSA). It extracts aspects and their associated opinion expressions and sentiment polarities from comment sentences. Previous studies have proposed a multitask learning framework that jointly extracts aspect and opinion terms and treats the sentiment analysis task as a table-filling problem. Although the multitask learning framework solves the problem of identifying overlapping opinion triples, the entire model cannot explicitly simulate interactions between aspects and opinions. Therefore, we propose a sentiment-dependence detector based on a dual-table structure that starts from two directions, aspect-to-opinion and opinion-to-aspect, to generate two sentiment-dependence tables dominated by two types of information. These complementary directions allow our framework to explicitly consider interactions between aspects and opinions and better identify triples. Moreover, we use a double-embedding mechanism—character-level and word-vector embeddings—in the model for triplet extraction that enables it to represent contexts at different granularity levels and explore high-level semantic features. To the best of our knowledge, this study presents the first bidirectional long short-term memory (BiLSTM) model based on double embedding used to perform ASTE tasks. Finally, our analysis shows that our proposed bidirectional sentiment-dependence detector and double-embedding BiLSTM model achieve more significant results than the baseline model for triples with multiple identical aspects or opinions.

Implementasi LSTM Pada Analisis Sentimen Review Film Menggunakan Adam Dan RMSprop Optimizer

Movies are an entertainment that is in great demand by many groups from children, teenagers, adults, and parents. In the current digital era, various films can be watched on television to digital streaming services. Public opinion on the films watched can be in the form of positive opinions or negative opinions. Sentiment analysis is one of the fields of Natural Language Processing (NLP) which is able to build a system to recognize and extract opinions in the form of text, sentiment analysis is usually used to find out people's opinions or assessments of a products, services, politics, or other topics. Through sentiment analysis from the collection of reviews, the public can get various recommendations for films that can be watched. The method implemented to classify review data into positive reviews and negative reviews in this study is LSTM by comparing two different optimizers, namely Adam and RMSprop. This study succeeded in providing sentiment predictions with different optimizers with accuracy values ??for the LSTM application with Adam Optimizer reaching 77.11% and the LSTM application with RMSprop reaching 80.07%.