Opinion Sentiment Analysis Research Articles

PERBANDINGAN KINERJA NAÏVE BAYES DAN SVM PADA ANALISIS SENTIMEN TWITTER IBUKOTA NUSANTARA

The national capital is the center of government of a country and is often a symbol of sovereignty and national identity. The function and role of the capital city is very important in coordinating government activities, public policies and community services. This research aims to compare the effectiveness of two approaches for classification: Support Vector Machine and Naïve Bayes (SVM), in analyzing opinion sentiment towards the Indonesian capital based on Twitter data. Opinion sentiment analysis is crucial for understanding public views regarding various aspects of the Indonesian capital. The Twitter data used will involve opinions developing on social media regarding the Indonesian capital. The research methodology involves data collection, preprocessing, data sharing, Naïve Bayes and SVM model training, evaluation, and statistical analysis to compare the performance of the two models. Naïve Bayes and Support Vector Machine are the approaches employed in this study. The research results from the Naïve Bayes method present a sentiment analysis accuracy rate of 91%. The SVM method also provides a sentiment analysis accuracy rate of 94%. In light of the analysis's findings, the procedure utilizing the Support Vector Machine (SVM) method shows better results than the Naïve Bayes method in measuring sentiment towards the Indonesian capital.

Development of decision-making technique based on sentiment analysis of crowdsourcing data in medical social media resources

The object of the study is the decision-making modeling in the context of medical social media to increase the clinics’ effectiveness. The problem is to classify the patient reviews collected in the patient-clinic segment of the medical social media and to identify the situation related to the clinics’ activity by revealing the criteria characterizing the clinics’ activity out of the opinions. The proposed technique refers to lexicon-based sentiment analysis of opinions, the classification based on Valence Aware Dictionary and Sentiment Reasoner (VADER), the verification of the results accuracy with Multinomial Naive Bayes and Support Vector Machine, the manual sentiment analysis of opinions to detect criteria and the classification of opinions according to each criterion. Using this technique, out of 442587 patient reviews obtained from database cms_hospital_satisfaction_2020 of the Kaggle company generated on the basis of crowdsourcing of patient reviews on medical social media, 218914 patient reviews are classified as positive, 190360 – as neutral, and 33313 – as negative. The results accuracy is verified, and the clinics are rated by the «positive» opinions. 6 new criteria characterizing the clinics’ activity are discovered, and the identification of the situation related to the clinics’ activity based on the comparison of «positive» and «negative» opinions according to each criterion is presented. The possibility of using the results obtained from the identification to increase the clinics’ efficiency in making decisions is shown. The results obtained in this study can be used to improve the clinics’ performance according to public opinion. This opportunity involves the crowdsourcing of opinions about the clinic in the medical social media environment and the collection of opinions in a structured way.

Research on sentiment analysis method of opinion mining based on multi-model fusion transfer learning

With the popularity of social media, opinion mining has gradually become a popular research field. Among these fields, sentiment analysis mining is an important research direction in the field of opinion mining. It aims to reveal the public's sentiment tendency, and attitude towards specific topics or events by analyzing text data generated by users on online platforms and digital media. However, the large amount of opinion data usually lacks effective annotation, which limits the learning and construction of opinion models. Therefore, focusing on the problem of the scarcity of labeled data in opinion analysis, this paper proposes a mining method for public opinion sentiment analysis based on multi-model fusion transfer learning, that can make full use of the limited labeled data to improve the learning efficiency of sentiment features by integrating the advantages of different models. Additionally, it introduces a transfer learning strategy to enable the models of the target domains to perform better in the absence of labeled data. Furthermore, the attention mechanism is combined to strengthen the acquisition of key features of the emotional colors and improve the accuracy of sentiment analysis. Specifically, the paper uses the ERNIE model to generate dynamic representations of the text word vectors in the dataset. It also uses TextCNN and BiGRU to construct a joint model for extracting local and overall features of the text word vectors. The parameters of the feature layer of the trained model are migrated to the target domain through transfer learning. The attention mechanism is combined with the model to identify the extreme elements of the sentiment. Finally, the local and overall features are fused to achieve comprehensive mining of public opinion and emotional information. This method can effectively improve the accuracy and generalization of public opinion analysis in cases of data scarcity. In the experimental part, the paper conducts comparisons and analyses in eight aspects: word embedding model, model combination, attention mechanism, transfer learning, source domain dataset, target domain dataset, model training, and baseline model. The four indicators, namely accuracy, precision, recall, and F1-measure are used to evaluate the performance of the method. The experiments are thorough and detailed, demonstrating the effective improvement of opinion mining performance.

Sentiment Analysis of Opinions about Online Education in the Kurdistan Region of Iraq during COVID-19

Sentiment analysis is widely used in various areas and has versatile applications. For example, it is used in market research, customer retention strategies, and product analysis, to name a few. Although a few works on the topic exist for the Kurdish language, similar to other fields in Kurdish processing, it is not well-studied, and particularly it suffers from data inadequacy. In this paper, we present research we conducted to analyze the sentiments of learners/educators toward online education during COVID-19 in the Kurdistan Region of Iraq. We collected the data from tweets tweeted in Kurdish (Sorani) up to March 2022. We used four Machine Learning algorithms: Naïve Bayes, SVM, Random Forest, and Logistic Regression, and analyzed their performance on our dataset. We retrieved about 600 tweets, which after preprocessing, yielded 511 items. We conducted five experiments, four of which included testing all algorithms using two scenarios of balanced and unbalanced datasets of positive/negative items, each using 80/20 and 90/10 training/testing data splitting methods. The fifth experiment included four parts, setting a limit for feature selection starting at 500 features and increasing it to 500 at a time until 2000 features, testing for both 80/20 and 90/10 data splitting approaches. The results showed that the best algorithm to build a sentiment analysis model is SVM, with an accuracy of 89% and a maximum feature selection of 1000. The dataset is publicly available for non-commercial use under CC0 1.0 Universal license.

From YouTube Comments to Insights: A Sentiment Analysis of Opinions on Productivity Tools

Abstract: YouTube, a diverse content hub, acts as a prominent platform for both viewing videos and engaging through comments that express opinions. By carefully analyzing these comments, sentiments associated with products or topics become evident. This research delves into sentiment analysis of YouTube comments, specifically focusing on sentiments towards productivity tools and technologies. Through this examination of conveyed sentiments, it deepens understanding of public perceptions and attitudes toward these tools. Utilizing YouTube's reach and engagement, the study systematically collects comment data using the YouTube API and employs the established VADER sentiment analysis framework. Employing a Bag-of-Words approach, the research incorporates machine learning algorithms like Naive Bayes and Random Forest, achieving accuracy rates of 84.01% and 91.34%, respectively. In-depth temporal analysis of user engagement patterns uncovers trends, with heightened engagement followed by decline, correlating with external events, notably the Covid-19 pandemic. These insights enhance sentiment analysis and illuminate dynamics between societal occurrences, user sentiments, and digital dialogues, offering perspectives on evolving opinions about productivity tools and technologies

Pembobotan TF-IDF Menggunakan Naïve Bayes pada Sentimen Masyarakat Mengenai Isu Kenaikan BIPIH

The Ministry of Religious Affairs proposes to increase the cost of Hajj Travel (Bipih) in 1444 H/2023 M to Rp.69.19 million. There is a fairly high increase in costs compared to 2022. This raises sentiment in the community, there are public opinions for and against the issue of rising Bipih on social media twitter. The purpose of this study was to analyze the sentiment on the issue of increasing the cost of Hajj Travel and to prove whether Naive Bayes is a good classifier of text on the issue of incremental sentiment. Naive Baye is one of the best text classifier algorithms. Data taken from social media twitter. The Data are grouped into pro and Contra opinions and then processed using python programming language and jupyter as text editor. Data used as much as 850 data. The Data is divided into training data and testing data with a ratio of 80:20. With the number of training data of 679 data and the number of testing data of 170 data. Then implement Multinominal Naive Bayes algorithm (MNB) as text classifier and word weighting using TF-IDF. The test results obtained accuracy value of 89% and ROC value of 0.91. It is proven that Multinominal Naive Bayes algorithm (MNB) is a good classifier of text for sentiment analysis of opinion on the issue of increasing the cost of Hajj travel because it is included in the Excellent Classification.

Sentiment Analysis to Predict Movies Success Rate Based on NLTK Movie Review Corpora Using Machine Learning

With the proliferation of social networks, peoples express their opinions about different things or issues on social media without any hesitation. The rapid growth of textual data on social media are required to develop algorithms and techniques for recognizing people’s opinions towards specific subject. These opinions are helpful in business plans development, marketing trends, political parties’ popularity. The film industry can be an important revenue generating industry of any country. Peoples express their opinion on movie trailer using social media. The effective sentiment analysis of opinions on social media such as Twitter can be helpful to predict movie ratings. This research work focuses on developing a technique to predict movie success rate on the basis of tweets data. We have collected tweets about different movies after their trailer released by using hash tag method. We applied Sentiment analysis approach using Machine learning. In this study we utilized four key algorithms (Naïve Bayes, SVM, Neural Networks, decision tree) on NLTK Movie review corpora.

Sentiment Analysis of Opinions on the Use of Devices in Students Using the Support Vector Machine (SVM) Method

Sentiment Analysis is a field of science in analyzing a sentiment or opinion on a particular object or problem and the opinion can be divided into several purposes (classes) that lead to negative, neutral or positive opinions. Gadgets (gadgets) are human aids in many fields including work, entertainment, communication and information, the use of gadgets themselves encompasses all ages including school students who use gadgets excessively that affect the mental, physical and attitudes of users. Twitter social media is one of the social media that is used by the public in making opinions about the influence of gadgets, especially parents, these opinions are useful for other users in determining the granting of access rights and direction for children, especially students in using gadgets. Opinion classification is needed in making it easier for other users to see whether opinions from the influence of gadgets fall into the negative, neutral or positive classes. The method used in the classification of opinion is Support Vector Machine (SVM). The data used in this study amounted to 1354 taken in 2019 using web scraping techniques on the Twitter site which are then pre-processed so that it can be processed into the program and classified into 3 classes of sentiments, namely negative, neutral and positive sentiments. In finding the average value of accuracy in the distribution of training data and test data using k-fold cross validation of 10-fold produces an average value of 85.3%. Then testing is done to measure the performance of the SVM method using confusion matrix in the percentage of training data and different test data and produces the highest accuracy value of 83.3%.

Exploratory Analysis of Fundamental Spiritual Support Factors to a Positive Attitude in Patients with COVID-19 Using Natural-Language Processing Algorithms

The SARS-CoV-2 virus that causes COVID-19 affects the respiratory tract and is highly infectious. Those patients who knew that the disease could cause death or that their healing process is quite painful because of the symptoms and conditions developed extreme stress, anxiety, and depression, which aggravated the effects of the disease. Therefore, it is vital to conduct research to analyze these effects and generate self-help and support mechanisms during the disease process. This paper presents exploratory analysis related to stress, coping attitudes, emotional responses, and sources of support that were vital in patients affected by COVID-19; the focus of this study is the consideration of the spiritual factor, which may influence religious resilience that allows for a positive attitude and tenacity. To carry out this research, interviews were conducted with patients who had suffered from COVID-19 disease, and the collected information was processed using text-mining techniques using a two-phase methodology. The first phase is based on the Colaizzi method. Interview responses were coded through the search for patterns in the key phrases, and these codes were grouped, forming semantic relationships. In the second phase, natural-language processing algorithms (WordCloud, WordEmbedding, sentiment analysis of opinions) were used, summarizing the interviews in relevant factors of the patient’s experience during the disease. Spiritual resilience stood out the most of all key phrases of the code group tables. Likewise, words such as security, confidence, tranquility, and peace indicated that the patients took a positive attitude towards the symptoms and complications of the disease. Therefore, it is important to be the resilience to face a crisis process, and one of the factors that generated such resilience in COVID-19 patients was religious faith, which was expressed in the interviews using the factors of security, trust, promises of healing, tranquility, and the impossibility of discouragement. All this contributed to the positive attitude of the interviewees during the process of recovery from the disease.

Evaluation of Cluster Management Quality Based on Consumer Opinion Sentiment Analysis

Abstract This article discusses the issue of assessing the quality of cluster management by utilizing Internet customer feedback about companies that are members of clusters. Due to the growing number of Internet users, companies pay greater attention to the opinions published about them. Consumers are also increasingly willing to share their opinions and thoughts about the products they use. As a result, it has become possible to analyze the quality of services and products provided by an enterprise based on Internet opinions. In this article, we analyze the quality of cluster management as reflected in the European Cluster Excellence Initiative (ECEI) label, as measured by sentiment analysis of Internet opinions. The paper proposes a method for the identification and evaluation of Internet sources used in the opinion sentiment analysis. Sentiment analysis of Internet opinions of cluster and in-cluster business customers was performed, and the results were compared with the level of the ECEI label, which was awarded to the analyzed clusters. The conducted research showed convergences between formalized systems of management quality assessment and the level of opinions expressed on the Internet. The results testify that sentiment analysis can complement the evaluation of cluster management quality.

Analysis of Sentiment of Moving a National Capital with Feature Selection Naive Bayes Algorithm and Support Vector Machine

The decision to move Indonesia's capital city to East Kalimantan received mixed responses on social media. When the poverty rate is still high and the country's finances are difficult to be a factor in disapproval of the relocation of the national capital. Twitter as one of the popular social media, is used by the public to express these opinions. How is the tendency of community responses related to the move of the National Capital and how to do public opinion sentiment analysis related to the move of the National Capital with Feature Selection Naive Bayes Algorithm and Support Vector Machine to get the highest accuracy value is the goal in this study. Sentiment analysis data will take from public opinion using Indonesian from Twitter social media tweets in a crawling manner. Search words used are #IbuKotaBaru and #PindahIbuKota. The stages of the research consisted of collecting data through social media Twitter, polarity, preprocessing consisting of the process of transform case, cleansing, tokenizing, filtering and stemming. The use of feature selection to increase the accuracy value will then enter the ratio that has been determined to be used by data testing and training. The next step is the comparison between the Support Vector Machine and Naive Bayes methods to determine which method is more accurate. In the data period above it was found 24.26% positive sentiment 75.74% negative sentiment related to the move of a new capital city. Accuracy results using Rapid Miner software, the best accuracy value of Naive Bayes with Feature Selection is at a ratio of 9:1 with an accuracy of 88.24% while the best accuracy results Support Vector Machine with Feature Selection is at a ratio of 5:5 with an accuracy of 78.77%.

A framework for ensuring zero defects and sustainable operations in major Indian ports

PurposePorts are a significant link in a global supply chain and an economic entity that contributes to the country's economy. India has around 200 ports along its coastline of about 8,000 Km, yet none of them perform at par with many Asian ports. In the Indian port system, cargo throughput and the turnaround time (TAT) of ships calling at ports constitute the most significant performance measures. These performance metrics do not integrate sustainability measures such as emission levels and energy consumed. The draft is a constraint in many ports and ships visit with less than full shipload cargo. The TAT for such vessels may be lower, but the emission per ton of cargo carried is higher compared to a ship with full shipload cargo. Many ports have old or poorly maintained equipment. This state of equipment increases pollution and consumption of energy. In this paper, an attempt has been made to address the issue of undesirable and right outputs simultaneously in an Indian port system. This paper proposes a framework to ensure zero defects in Indian port operations and a port-sustainability-index to measure sustainable services in Indian ports.Design/methodology/approachThe authors used data envelopment analysis (DEA) to show that all private terminals did not perform efficiently and contradicted the notion of Indian policymakers that privatization will lead to an increase in performance levels. A literature review was carried out to identify the dimensions and factors that affect ports' performance. A case study of a major port in India and expert group discussion was done to ascertain the views of stakeholders on deficiencies in the system. The authors complemented this approach with sentiment analysis of opinions expressed by stakeholders over a while, using SentiStrength analysis software (Thelwell, 2010, 2012). The authors used the combined findings to develop the port-sustainability-index (PSI), identify the research question, and develop an ontology of the port system. The authors use the concepts of ontology-design-pattern (ODP) and logistics-service-map (Glöckner et al., 2014; Glöckner and Ludwig, 2016, 2017), opinion mining (Pang and Lee, 2008) and competency questions (Glöckner and Ludwig, 2017) to develop a port system map followed by the identification of critical elements; and the flows (physical and information flow) that gets disrupted due to defects in the system. The ontology led to the identification of competencies and capabilities a port needs to possess. Based on these identification process competency questions were drawn, and the authors identified the plausible defects that port may encounter. The authors suggested the sustainability metrics for monitoring port performance and policy changes based on the competency questions, defects, and mitigation plans.FindingsThe authors introduced four KPIs, namely, port-sustainability-index (PSI), load factor (lx and ly), draft ratio (dr), and turnaround-time ratio (TATR). The authors suggested significant policy changes for Indian ports. These included –(1) Introduction of virtual arrival (VA) policy, reducing randomness in the system by pre-scheduling arrivals and activities. (2) Redefining economic life of equipment and machinery in terms of expenditure, income and desired levels of output. (3) Pricing port charges based on stakeholders’ ability and willingness to pay. The port needs to declare its productivity levels and frame their charges accordingly. (4) The ports need to frame an output-oriented privatization policy where it specifies the growth of the port. (5) Framing vessel pricing policy where a vessel may pay tax for the use of non-clean fuel or a get discount for bringing higher parcel load. (6) Levy lower port charges for the shipper for transporting cargo by rail and barges. (7) Introduce a differential pricing system where port levies lower charges for export cargo compared to import load.Research limitations/implicationsThe research work can be extended to develop a simulation model to carry out policy experimentations concerning the improvement of performance and carry out sustainable operations. Alternatively, researchers may develop a multi-criteria optimization model to determine the best course of action, keeping the objective function as minimization of PSI value.Practical implicationsThis paper provides the means to the Indian ports to remain competitive, lower emission levels and energy consumption, and optimize emission per ton of cargo handled in the port.Social implicationsSociety significantly benefits from this study as it recommends ways to minimize pollution that has a significant impact on human lives. Besides, the measures suggested in the paper will lower the cost of exports and imports, enhancing the real income of consumers.Originality/valueThe area of sustainable port operations has previously been under-researched in the Indian context. Authors contribute to the sustainable port operation literature by suggesting a port-sustainability-index, a framework to assess the defects in port operation and development of a port-ontology for further research in the area of a port system.

Community Opinion Sentiment Analysis on Social Media Using Naive Bayes Algorithm Methods

The election of Governor is an election event for the Regional Head for the future of the region and the country. The Central Java Governor election in 2018 was held jointly on 27 June 2018, which was followed by 2 candidate pairs of the governor. Its many responses from people through twitter's social media to bring up opinions from the public. Sentiment analysis of 2 research objects of Central Java Governor 2018 candidates with a total of 400 tweets with each candidate being 200 tweets. The used of tweets are divided into 3 classes: positive class, neutral class and negative class. In this study the classification process used the Naive Bayes Classifier (NBC) method, while for data preprocessing is using Cleansing, Punctuation Removal, Stopword Removal, and Tokenisation, to determine the sentiment class with the Lexicon Based method produces the highest accuracy in the Ganjar Pranowo dataset with an accuracy of 87,9545%, Precision value is 0.891%, Recall value is 0.88% and F-Measure is 0.851% while Sudirman Said dataset has an accuracy rate of 84.322%, Precision value of 0.867%, Recall value of 0.843% and F-Measure of 0.815%. From these results, we can conclude that the Ganjar Pranowo dataset was higher compared to Sudirman Said's dataset.

Application of the consensus method in a multiagent financial decision support system

Financial decisions are supported by different methods, based mainly on statistics, mathematics, behaviorism, artificial intelligence or experts' opinion sentiment analysis. The main problem is that under conditions of risk and uncertainty predicting financial markets can be very difficult. This paper presents an approach to investment strategy design for a multiagent system which supports investment decisions on the stock market. Individual components and functionalities of the multiagent financial decision support system method have been briefly described. On the basis of decisions generated by agents, the Supervisor Agent uses a consensus method to generate a satisfactory rate of return and reduce the level of risk associated with investing in a financial instrument. Verification of the effectiveness of the strategy has been conducted using investments on the Warsaw Stock Exchange.