An Optimal Clustering with Hybrid Metaheuristic Algorithm for Sentiment Analysis and Classification

Sentimental Analysis (SA) becomes a familiar topic among business people, which is commonly applied for the classification of sentiments from online reviews. It is generally treated as a sentiment classification (SC) problem where the online reviews are categorized into positive or negative polarities using the words that exist in the online reviews. With this motivation, this paper presents a new K-means clustering with hybrid metaheuristic algorithm (KMC-HMA) for SA and classification. The proposed KMC-HMA technique initially performs data preprocessing to remove the unwanted words from the product reviews. In addition, K-means clustering technique is used for the clustering of the massive quantity of the applied product reviews. Moreover, the clustered data are fed into the classification model based on hybrid ant colony optimization (ACO) with dragonfly algorithm (DFA). The ACO algorithm is used for the classification of product reviews and the performance of the ACO algorithm can be optimally tuned by the use of DFA. The performance validation of the KMC-HMA technique is validated using two datasets such as Canon and ipod. The experimental values pointed out the superior performance of the KMC-HMA technique over the recent state of art techniques.

Document-level sentiment classification is dedicated to predicting the sentiment polarity of document-level reviews posted by users about products and services. Many methods use neural networks have achieved very successful results on sentiment classification tasks. These methods usually focus on mining useful information from the text of the review documents. However, they ignore the importance of users’ review habits. The reviews posted by the same user when commenting on different products contain similar review habits, and reviews that contain highly similar review habits often have similar sentiment ratings. In this paper, we propose a novel sentiment classification algorithm that utilizes user’s review habits to enhance hierarchical neural networks, namely as HUSN. Firstly, we divide the reviews in the training set according to the users. All the reviews of each user are aggregated together and called the historical reviews of this user. Secondly, the target review in the test set and its multiple historical reviews in the training set are sent to the Long Short-Term Memory based hierarchical neural network to obtain the corresponding review document representations containing the user’s review habits. Finally, we calculate the similarities between the target review document representation and multiple historical review document representations. The higher the similarity, the closer the review habits of different reviews from the same user, and the closer the corresponding sentiment ratings. Experimental results show that the similarities between the review habits of different reviews from the same user can further improve the performance of document-level sentiment classification. The HUSN algorithm performs better than all baseline methods on three publicly available document-level review datasets.

Chips are a well-known product among Small and Medium Enterprises (SMEs). In order to enhance the quality of chips as an SME product, sentiment analysis is a crucial step. In this research, sentiment analysis of chip purchases on the Shopee E-marketplace was conducted using the Natural Language Processing (NLP) method, utilizing the N-Gram Model and Term Frequent-Inverse Document Frequency (TF-IDF) as feature extraction techniques, and the Support Vector Machine (SVM) algorithm for sentiment classification. The objective of this research is to identify the most suitable feature extraction model and optimal SVM kernel type from the options of Linear, Polynomial degree, Gaussian RBF, and Sigmoid kernels. Results from the experiments indicate that the TF-IDF and unigram feature extraction techniques offer the best performance for SVM classification when utilizing the Linear kernel. By labeling the dataset, it was observed that using a lexicon-based approach for sentiment classification resulted in 84.31% of the total reviews being positive. The words "price", "cheap" and "quality" in unigram have the highest weights above 0.040. In the unigram model, linear kernel accuracy and precision performance values are 88.4% and 87.3%. At the same time, the recall performance values is 88.4%. The results of the F1-Score assessment matrix from Unigram were 86.9%, Bigram was 78.5% and Trigram was 77.4%. Ultimately, the unigram model combined with a linear kernel in the SVM algorithm demonstrates strong potential for application in the development of various systems focused on detecting user reviews in the Indonesian language on the Shopee E-Marketplace.

With the advent of the Internet, there have been many changes. As existing means of off-line communication have transferred to the Internet, a wide range of multimedia services are emerging. And unlike in the past, these work as tremendous sources from which people’s opinions and attitudes can be obtained. Particularly, diverse opinions and reviews posted on the web in real time help corporations or the State establish the directions of policies. In this context, this study developed machine learning-based environment issue sentiment classifier in order to find out, from comments posted below news, how people recognize issues about climate change in terms of environment. Based on training data constructed by this study, a sentiment classification algorithm was constructed by applying SVM (support vector machine) and Naive Bayes, which are machine learning techniques, and a sentiment classifier was constructed by applying CNN (convolutional neural networks) and Bi-LSTM (bidirectional long-short term memory) techniques among deep learning techniques recently researched vigorously; and then their performance was compared.

Over the last few years, digital text data is increasing with the advancement in use of technologies. Therefore, sentiment analysis is an important step for improving the performance of any classifier. But with the increase in data, this problem has become more complex. To improve the overall performance of classifier and reducing the data-dimensionality, Feature selection is a key sub-stage for the sentiment analysis. In this paper, we propose a feature selection approach, which is based on a novel variant of hybrid differential evolution algorithm and PSO for sentiment classification. Experimental results show that our approach achieves 97.56% and 98.54% of average accuracy by using Naive Bayes (NB) classifier for the two Twitter datasets, viz., TestData_2015 and twitter sanders, respectively. The results also show that our proposed approach is showing better results with state-of-art algorithms on Twitter datasets. Statistical results also showcase the effectiveness of our proposed model.

Sentiment classification, which uses deep learning algorithms, has achieved good results when tested with popular datasets. However, it will be challenging to build a corpus on new topics to train machine learning algorithms in sentiment classification with high confidence. This study proposes a method that processes embedding knowledge in the ontology of opinion datasets called knowledge processing and representation based on ontology (KPRO) to represent the significant features of the dataset into the word embedding layer of deep learning algorithms in sentiment classification. Unlike the methods that lexical encode or add information to the corpus, this method adds presentation of raw data based on the expert’s knowledge in the ontology. Once the data has a rich knowledge of the topic, the efficiency of the machine learning algorithms is significantly enhanced. Thus, this method is appliable to embed knowledge in datasets in other languages. The test results show that deep learning methods achieved considerably higher accuracy when trained with the KPRO method’s dataset than when trained with datasets not processed by this method. Therefore, this method is a novel approach to improve the accuracy of deep learning algorithms and increase the reliability of new datasets, thus making them ready for mining.

The rapid development of information technology has changed the way people interact and express their opinions on public policies, including the People's Housing Savings (Tapera) policy in Indonesia. People now primarily express their views openly on social media platforms like Twitter, generating a substantial amount of text data for analysis to understand public sentiment. However, the main challenge in this sentiment analysis is determining the most effective machine learning algorithm for classifying public opinion with high accuracy. This study aims to compare the performance of three machine learning algorithms, namely Naïve Bayes, Support Vector Machine, and Random Forest, in analyzing public sentiment towards the Tapera policy. This study analyzes public comment data obtained from Twitter. We measure the accuracy of each algorithm to determine its optimal performance in sentiment classification. The research method consists of several stages, starting with data collection, text preprocessing to clean and prepare data, and then applying the three algorithms to analyze sentiment. The results showed that Naïve Bayes had the highest accuracy of 69.17%, followed by Support Vector Machine with an accuracy of 68.42%, and Random Forest with an accuracy of 66.17%. This shows that Naïve Bayes is the most effective algorithm to use in sentiment analysis of public comments related to the Tapera policy, especially in the context of complex text data from social media. The conclusion of this study is that Naïve Bayes is superior in classifying public sentiment towards the Tapera policy compared to Support Vector Machine and Random Forest. As a result, this study makes a significant contribution to selecting the most appropriate machine learning algorithm for public sentiment analysis towards public policy, which in turn can help the government understand and respond to public perceptions more effectively.

This study explores public sentiment toward the Merdeka Curriculum, a policy reform introduced to address educational challenges in Indonesia following the COVID-19 pandemic. Utilizing Twitter (now X) as a data source, this research collected 1,900 Indonesian-language tweets to assess how society perceives the curriculum’s flexibility and relevance. The analysis begins with data preprocessing, including cleaning, tokenization, stopword removal, and stemming. VADER (Valence Aware Dictionary and Sentiment Reasoner) is employed for initial sentiment labeling, classifying tweets into positive, neutral, and negative categories. The results reveal a significant class imbalance: 1,692 neutral, 117 positive, and 91 negative tweets. These labeled tweets are further analyzed using the Long Short-Term Memory (LSTM) algorithm for deep sentiment classification. The LSTM model demonstrates training accuracy improvements from 82% to 90.29% across five epochs, while validation accuracy remains steady at 88%. However, the model fails to accurately classify minority classes, with precision, recall, and F1-scores for positive and negative sentiments scoring zero. This indicates that while LSTM can effectively recognize the dominant neutral sentiment, it struggles with minority class identification due to data imbalance. The findings highlight the need for improved model training strategies and data augmentation to enhance classification performance across all sentiment categories. Overall, this study contributes to the integration of lexicon-based and deep learning approaches for sentiment analysis and offers valuable insights for educators and policymakers in optimizing the Merdeka Curriculum through data-informed decisions.

The growth of the tourism sector in Palembang City has encouraged an increase in the need for quality hospitality services. In the digital age, user reviews on the Google Maps platform are an important source of data to assess customer satisfaction. This study aims to analyze and compare the effectiveness of two sentiment classification algorithms, namely Support Vector Machine (SVM) and Random Forest, in processing hotel reviews in Indonesian. A total of 1000 review data was used and processed through the stages of text cleanup, letter normalization, tokenization, stopword removal, and stemming. The evaluation was carried out with two approaches: 80:20 data sharing and cross-validation using the K-Fold technique. On data sharing, Random Forest showed 88% accuracy and 100% recall, while SVM recorded 87% accuracy and 99% recall, with equivalent precision and F1-score. However, cross-validation showed that the SVM was more stable and consistent, with 92% accuracy, 94% accuracy, 98% recall, and 96% F1-score, outpacing Random Forest's 91% accuracy and 95% F1-score. These results show that the SVM algorithm is superior in analyzing hotel review sentiment on Google Maps. These findings provide recommendations for tourism information system developers to adopt an SVM-based approach to review data processing to support more accurate and responsive decision-making.

Sentiment analysis is a field of computational linguistics involving identification, extraction, and classification of opinions, sentiments, and emotions expressed in natural language. Sentiment classification algorithms aim to identify whether the author of a text has a positive or a negative opinion about a topic. One of the main indicators which help to detect the opinion are the words used in the texts. Needless to say, the sentiments expressed in the texts also depend on the syntactic structure and the discourse context. Supervised machine learning approaches to sentiment classification were shown to achieve good results. Classifying texts by emotions requires finer-grained analysis than sentiment classification. In this thesis, we explore the task of emotion and mood classification for blog postings. We propose a novel approach that uses the hierarchy of possible moods to achieve better results than a standard flat classification approach. We also show that using sentiment orientation features improves the performance of classification. We used the LiveJournal blog corpus as a dataset to train and evaluate our method. Another contribution of this work is extracting paraphrases for emotion terms based on the six basics emotions proposed by Ekman (happiness, anger, sadness, disgust, surprise, fear). Paraphrases are different ways to express the same information. Algorithms to extract and automatically identify paraphrases are of interest from both linguistic and practical points of view. Our paraphrase extraction method is based on a bootstrapping algorithms that starts with seed words. Unlike in previous work, our algorithm does not need a parallel corpus. In Natural Language Generation (NLG), paraphrasing is employed to create more varied and natural text. In our research, we extract paraphrases for emotions, with the goal of using them to automatically generate emotional texts (such as friendly or hostile texts) for conversations between intelligent agents and characters in educational games. Nowadays, online services are popular in many disciplines such as: e-learning, interactive games, educational games, stock market, chat rooms and so on. NLG methods can be used in order to generate more interesting and normal texts for such applications. Generating text with emotions is one of the contributions of our work. In the last part of this thesis, we give an overview of NLG from an applied system's points of view. We discuss when NLG techniques can be used; we explained the requirements analysis and specification of NLG systems. We also, describe the main NLG tasks of content determination, discourse planning, sentence aggregation, lexicalization, referring expression generation, and linguistic realisation. Moreover, we describe our Authoring Tool that we developed in order to allow writers without programming skills to automatically generate texts for educational games. We develop an NLG system that can generate text with different emotions. To do this, we introduce our pattern-based model for generation. We show our model starts with initial patterns, then constructs extended patterns from which we choose final'' patterns that are suitable for generating emotion sentences. A user can generate sentences to express the desired emotions by using our patterns. Alternatively, the user can use our Authoring Tool to generate sentences with emotions. Our acquired paraphrases will be employed by the tool in order to generate more varied outputs.

This project explores visitor experiences by conducting sentiment analysis and clustering analysis on 1,973 visitor reviews posted on Google Maps and TripAdvisor. Utilizing machine learning algorithms like Support Vector Machine (SVM) and the K-Means algorithm, the project achieved 87.66% accuracy in sentiment classification and identified three optimal clusters. Then, a detailed analysis of both results were conducted. The insights are visualized through an interactive dashboard, enabling museum management to make informed decisions. Despite data limitations, the project offers strategic recommendations for ongoing improvement, aiming to enhance visitor satisfaction and engagement at the Terengganu State Museum.

In the last few years, with rapid growth in use of networking sites such as twitter and Facebook has been increased greatly. This also attracted the researcher to use social networks data for sentiment analysis. Sentiment analysis is also known as opinion mining is the process of finding out the emotion such as positive, negative and neutral from the series of words. In present, on internet huge amount of data has been generated and to extract useful information from data is also become interest for the researchers. Sentiment analysis has been done mostly in English and Chinese languages. In this paper, sentiment classification is done on Urdu news tweets. The proposed methodology consists upon two steps. In first step data preprocessing is done such as removal of hash tag and removal of stop words is done. In second step feature vector is designed. The feature vector is formulated by through the identification of number of positive words, negative words, and presence of negation and use of POS tags. After formulation of feature vector the decision tree is used as classification algorithm. The decision tree classifies the tweet as positive, negative and neutral. The experimental result of the proposed methodology shows significant success in terms of accuracy and sentiment analysis.

The rapid growth of financial technology (fintech) services in Indonesia has significantly transformed digital transaction behavior, with digital wallets such as DANA becoming widely adopted. Despite high usage rates, public discourse on social media frequently highlights both positive experiences and recurring concerns related to system reliability and data security. Twitter, as a real-time public communication platform, provides a rich source of user-generated content that reflects public perception toward fintech services. This study investigates public sentiment toward DANA fintech services in Indonesia through sentiment analysis of Twitter data using machine learning approaches. Purpose:This study aims to analyze public perception of DANA fintech services based on sentiment expressed on Twitter and to compare the performance of several machine learning classification algorithms in identifying positive, neutral, and negative sentiments in Indonesian-language social media texts. Methods/Study design/approach: The study employs a quantitative descriptive approach using text mining and sentiment analysis techniques. Twitter data were collected via the Twitter API over a specified period and processed through preprocessing stages including text cleaning, tokenization, stopword removal, and stemming. Feature extraction was performed using the Term Frequency–Inverse Document Frequency (TF-IDF) method. Sentiment classification was conducted using Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Random Forest algorithms. Model performance was evaluated using accuracy, precision, recall, and F1-score metrics. Result/Findings:The results indicate that public sentiment toward DANA is predominantly positive, driven by perceptions of transaction convenience and speed, followed by neutral sentiment, while negative sentiment is mainly associated with system disruptions and data security issues. Among the evaluated algorithms, SVM achieved the highest classification accuracy (91.4%), outperforming Random Forest and KNN. These findings demonstrate that SVM is more effective for sentiment classification of short Indonesian-language texts on social media platforms. Novelty/Originality/Value:This study contributes to the growing body of sentiment analysis research in Indonesia by providing empirical evidence on public perception of fintech services using machine learning techniques. By systematically comparing multiple classification algorithms in the context of Indonesian Twitter data, the study offers methodological insights and practical implications for fintech service providers in improving service quality, communication strategies, and user trust.

Due to the diversity of text expressions, the text sentiment classification algorithm based on semantic understanding is difficult to establish a perfect sentiment dictionary and sentence matching template, which leads to strong limitations of the algorithm. In particular, it has certain difficulties in the classification of student sentiments. Based on this, this paper analyzes the student sentiment classification model by neural network algorithm and uses the student group as an example to explore the application of neural network model in sentiment classification. Moreover, the regularization method is added to the loss function of LSTM so that the output at any time is related to the output at the previous time. In addition, the sentimental drift distribution of sentimental words on each sentimental label is added to the regularizer, and the sentimental information is merged with the two-way LSTM to allow the model to choose forward or reverse. Finally, in order to verify the research model, the performance of the model proposed in this paper is studied through experimental research. The research shows that the model proposed in this paper has better comprehensive performance than the traditional model and can meet the actual needs of students’ sentiment classification.

Background: With the tremendous increase in the use of social networking sites for sharing the emotions, views, preferences etc. a huge volume of data and text is available on the internet, there comes the need for understanding the text and analysing the data to determine the exact intent behind the same for a greater good. This process of understanding the text and data involves loads of analytical methods, several phases and multiple techniques. Efficient use of these techniques is important for an effective and relevant understanding of the text/data. This analysis can in turn be very helpful in ecommerce for targeting audience, social media monitoring for anticipating the foul elements from society and take proactive actions to avoid unethical and illegal activities, business analytics, market positioning etc. Method: The goal is to understand the basic steps involved in analysing the text data which can be helpful in determining sentiments behind them. This review provides detailed description of steps involved in sentiment analysis with the recent research done. Patents related to sentiment analysis and classification are reviewed to throw some light in the work done related to the field. Results: Sentiment analysis determines the polarity behind the text data/review. This analysis helps in increasing the business revenue, e-health, or determining the behaviour of a person. Conclusion: This study helps in understanding the basic steps involved in natural language understanding. At each step there are multiple techniques that can be applied on data. Different classifiers provide variable accuracy depending upon the data set and classification technique used.