Neutral Sentiment Research Articles

UTILIZING TWITTER DATA TO UDERSTAND GLOBAL HALAL INDUSTRY TRENDS AND DEVELOPMENTS IN THE DIGITAL ERA

Abstract
 The research aims to identify and collect issues related to the halal industry discussed by users' activities, sentiments, and content on Twitter. The method used involved collecting 135,050 Twitter conversations over a two-year period from July 21, 2021, to March 15, 2023, utilizing the Drone Emprit Academic (DEA) machine. Text data mining techniques were employed with the assistance of the DEA system, which included sentiment analysis, Social Network Analysis (SNA), and other descriptive analyses. The research findings indicate that the highest number of tweets related to the halal industry originated from Indonesia, followed by Malaysia and the United Kingdom. These tweets were predominantly contributed by millennials and zillennials and were characterized by a 71% positive sentiment, 27% negative sentiment, and 2% neutral sentiment. Furthermore, the Social Network Analysis (SNA) revealed integration and collaboration between the halal industry and Islamic financial institutions, suggesting the potential for creating a halal ecosystem. This research serves as a guideline for policymakers in the halal industry sector to evaluate public sentiment and formulate appropriate advancement strategies. Additionally, this study contributes to a deeper understanding of social media data analysis in the context of the halal industry and offers directions for future research.
 Keywords: Halal Industry; Text Mining; Sentiment Analysis; Twitter; Drone Emprit Academic.

Recommendation and sentiment classification on E-Commerce reviews

Due to the improvement of online shopping mode, an increasing number of customers rely on reviews displayed on online shopping websites to choose products, and there are also more and more sellers taking consumers' text reviews into consideration to modify their products. Therefore, understanding and analyzing these reviews are getting increasingly significant. This study utilized natural language processing on E-Commerce Reviews. First, I used the Nave Bayes model and Support Vector Machine to classify whether a reviewer recommends the reviewed product; the accuracies are both 87%. Then I used the random forest to classify the reviewer's positive, neutral, and negative sentiment on each review, which gave 86% precision.

Identifying Improvement Strategic from User Application Reviews Group Using K-Means Clustering and TF-IDF Weighting

PT ABC is one of the companies that provide online ticket-purchasing facilities amidst the rise of the digitalization era. So, companies need to see how application users complain as a form of evaluation and improvement. The rating results given by application users show a score of 3.3 from 172,000 reviews. The review results that will be examined are user reviews from January 2022 to April 1, 2023, which is more or less the last year of user comments. This research aims to form a review group using K-Means Clustering, the Elbow method, TF-IDF weighting, and analysis of review improvement strategies. The Elbow method is used to determine the optimal number of clusters so as not just to use assumptions. The success of the Elbow method in processing categorical data can be supported by assigning weights based on word frequency sequences using TF-IDF. The research analysis results show the formation of 4 clusters, with two tending to have negative sentiment, one neutral sentiment, and one positive sentiment. Mapping is carried out on each cluster to find out the characteristics of each cluster and possible causes of reviews, as well as providing solutions and strategies as a form of improvement. The problem of negative reviews appearing in each review group is different. It can be corrected with the proposed strategies, such as improving the appearance of features at the registration, ordering, and payment stages, adding payment methods, and carrying out regular system maintenance.

PUBLIC PERCEPTION OF AMIL ZAKAT INSTITUTIONS IN INDONESIA: INSIGHT DISCOVERY FROM MACHINE LEARNING

Introduction: This study aims to identify the most popular topics and words in conversations on Twitter with the topic of Amil Zakat in Indonesia. This research also aims to identify the sentiments and emotions of netizens about the Amil Zakat in Indonesia. Method: This study uses a qualitative method with a sentiment analysis approach with the help of Orange Data Mining. The data used are tweets from Twitter taken from 16 to 23 April 2023. Researchers used the keywords "Amil Zakat" "Lembaga Zakat" and "Lembaga Amil Zakat" to get a total of 1,000 tweets. Result: The results of the study show that the words "Zakat" "Badan" and "Nasional" are the three words that appear most often in discussions of Amil Zakat institutions on Twitter. These three words refer to the BAZNAS, where based on the metadata processed in this study, many people, individuals, and institutions distribute their zakat through BAZNAS. Conclusion and suggestion: Overall, Twitter is dominated by tweets with neutral sentiments, shown by happy emotions, as much as 93.51% of the total tweets. Amil Zakat can increase the intensity of communication through social media especially regarding solicitations for the community, as well as achieving the collection and distribution of zakat funds as a form of information disclosure to the public.

Sarcasm Detection in News Headline Dataset with Ensemble Deep Learning Method

Sarcasm, a prevalent linguistic device, is frequently used in public discourse, often causing offence and distress to the listener. The complexity inherent in detecting sarcasm is a significant and ongoing challenge in the field of sentiment analysis research. The widespread use of this phenomenon in diverse conversational contexts further complicates its identification in data sets full of human interactions. Deficiencies in methodologies for distinguishing such statements adversely affect the performance of sentiment analysis, especially in distinguishing negative, positive or neutral sentiments. Inaccuracies in sarcasm detection can affect the classification results of sentiment analysis. Therefore, sentiment analysis seeks to categorise sarcastic sentences that, despite appearing positive, actually contain negative meanings. This research aims to build a deep learning ensemble stack model. The basic deep learning methods used are Bidirectional Gated Recurrent Unit (BiGRU) and Convolutional Neural Network (CNN). LightGBM is used to perform stack ensemble of deep learning methods. The dataset used comes from the Kaggle website and consists of English headlines. The findings show that the stack ensemble method outperforms BiGRU and CNN, evidenced by an accuracy rate of 91.2% and an F1 score of 90.2%. Therefore, from the above discussion, it can be concluded that the LightGBM method emerges as the optimal solution for sarcasm detection

ANALYSIS OF THE EXISTENCE OF THE ACCOUNTING PROFESSION IN THE ERA OF SOCIETY 5.0 WITH THE NAIVE BAYES METHOD

Society 5.0 has opened a new phenomenon that allows humans to use modern-based science (Artificial Intelligence) for human needs with the goal of human life more easily. This phenomenon opens up various new possibilities and risks simultaneously. These changes have had a significant impact on the development of the accounting profession, resulting in fewer human resources needed in business, including accounting staff. This research aims to 1) Apply sentiment analysis to the existence of the accounting profession in the era of society 5.0. 2) Application of the naive Bayes method to classify sentiment analysis for the existence of the accounting profession in the era of society 5.0. 3) Testing the naive Bayes algorithm in sentiment analysis for the existence of the accounting profession in the era of society 5.0. This research design uses quantitative research, analysis of student sentiment on the existence of the accounting profession was carried out using data from 432 student opinions from several campuses in the East Java region. Test data using the Naïve Bayes algorithm with Term-Frequency Inverse Document Frequency feature selection and the Lexicon method. The results of this research are divided into five parts consisting of the first part 424 students' opinions on the level of accuracy (78%), the second part 427 students' opinions on the level of accuracy (62%), the third part 429 students' opinions on the level of accuracy (47%), the fourth part 425 students' opinions level of accuracy (56%), fifth part 429 student opinions level of accuracy (52%). It was found that the number of positive sentiments was more dominant than negative or neutral sentiments

Productive Zakat: An Intertemporal Sentiment Analysis

This study aims to measure public sentiment towards productive zakat by analyzing scientific publications from 1991 to 28 November 2023 using secondary data from the Scopus database. The research sample consists of 43 scientific publications indexed in Scopus. The results show that positive sentiment dominates with a percentage of 42%, while neutral sentiment occupies the second position with a percentage of 32%. Negative sentiment reached 26%. In the context of intertemporal analysis, 2020 recorded the highest number of sentiments throughout the period with 9 sentiments. Positive sentiment reached its highest peak in 2020 and 2021, with 4 sentiments each. Neutral sentiment reached its highest peak in 2019 and 2020, each with 3 sentiments. The year 2021 is characterized by a high number of negative sentiments, reaching 3 sentiments in that year. These findings provide an overview of the dynamics of public sentiment towards productive zakat during the study period and show the changing trends in views revealed through scientific publications

Twitter Analysis on Waqf and Health

This study aims to observe the evolution of public sentiment towards waqf health around the world. This research approach uses primary data by taking samples from Twitter tweets during the period 2011-2023. Sentiment analysis was conducted using VADER Python programming to classify sentiment into positive, negative and neutral. The results showed that India was the country with the largest distribution of tweet data discussing the issue of waqf health. Furthermore, positive sentiments dominate the discussion on the Twitter platform, reaching 63.2% of the total sentiments expressed. On the other hand, negative sentiments took second place with a contribution of 21.1%. Although neutral sentiment was the least, it still accounted for 15.8% of the total sentiment expressed in the discussion. Through this approach, this research provides a more in-depth picture of how people's views on waqf health evolve over time. This sentiment data can serve as a basis for further understanding of the global perception of waqf health initiatives

Sentiment Analysis to Measure Public Trust in the Government Due to the Increase in Fuel Prices Using Naive Bayes and Support Vector Machine

The study examines public sentiment on the government's fuel price policy using an experimental approach and Twitter data obtained through API scraping. It applies sentiment analysis methods like Naïve Bayes, SVM, and Majority Voting. SVM achieved 85% accuracy, excelling in identifying negative sentiments, while Majority Voting reached 70% by considering confidence levels. Naïve Bayes struggled with neutral sentiments. They are combining methods to enhance the understanding of public sentiments on fuel price changes. The study highlights sentiment analysis' effectiveness in gauging reactions to fuel policies, with SVM offering more profound insights into sentiments related to fuel price hikes. Challenges remain in identifying neutral sentiments due to social media text brevity. These findings underscore the contextual importance of interpreting sentiment analysis. Leveraging these insights, governments can understand public perceptions better and devise improved communication strategies for sensitive economic policies like fuel price hikes, fostering better government-citizen interactions. The study aims to guide stakeholders in comprehending public perspectives within public policy, emphasizing the relevance of sentiment analysis for policy evaluation.

Risk communication and Covid-19 through the lens of anonymous sources

The extent of the Covid-19 pandemic and the health, social and economic crisis it caused, brought additional burden to journalists, but also new power. At a time when the pandemic dominated the media space, the media assumed a key role in explaining, interpreting and offering help in understanding the pandemic to the public. Reporting on the pandemic brought many challenges for journalists, as they had to adapt their activities in accordance with the new reality. When communicating about risks and reporting on sensitive topics that have a great social impact, to which the pandemic and Covid-19 undoubtedly belong, it is even more important that media reporting is based on ethical and professional standards, to be responsible and transparent. Especially in risk communication, in times of crisis, reliable and verified information must be provided to the public. In the study, we were interested in the research of the reliance of journalists on anonymous sources in reporting on the pandemic. The paper’s aim is was analyze the frequency of use of anonymous information according to different topics, type and tone of information, to see if anonymous media sources’ use varied in times of a pandemic. Articles about Covid-19 contained more primary information, but less secondary and tertiary anonymous information. In Covid-19 articles more anonymous information with neutral sentiment was presented, but, at the same time, there was less information with negative sentiment and no information with positive sentiment. Particularly worrying was a low share of articles with included clarification on granting anonymity, on the other hand, there were significantly more verified sources of anonymous information with Covid-19 articles.

Multilingual Code-Mixed Sentiment Analysis in Hate Speech

Sentiment analysis discovers the emotion expressed in a text. It helps in analyzing the product reviews, customer feedback and survey responses. Researchers have developed various algorithms for this purpose, however, they have majorly focused only on the sentiment analysis in English language. Although, few works are available for Hindi and multilingual sentiment analysis, however, these works are not efficient enough to perform sentiment analysis in code-mixed languages. To overcome the limitation of the existing works, this paper presents a multilingual code-mixed language model which identifies the sentiments of the hate speech dataset extracted from Twitter. As the hate speech dataset with sentiment labels are not available, we first collect the data from Twitter. After that we label the data using a transformer-based pretrained sentiment analysis model trained on a large corpus of tweets in multiple languages. We pass our collected data as test data to this model and predict the sentiment labels. Now, we train six different machine learning models to perform our own task i.e sentiment analysis for multilingual code-mixed hate speech dataset. The machine learning models perform well across multiple languages and also code-mixed languages. In future, it can be easily adapted to different classification tasks based on code-mixed languages. The results yield that hate speech invokes negative sentiment whereas non-hate speech reflects either positive or neutral sentiment.

Public’s perception on nursing education during the COVID-19 pandemic: SENTIMENT analysis of Twitter data

With the emergence of nurses as heroes on the front lines during the COVID-19 pandemic, posts on Twitter about nursing and nursing education began to increase. This study aims to make a sentiment analysis on Twitter posts regarding society's perception of nursing education during the COVID-19 pandemic and to shed light on concerns, sentiments, and experiences related to nursing education during the pandemic. The text mining method was used to analyze the sentiment analysis of Twitter data. Between July 1st, 2021, and July 1st, 2022, during the COVID-19 pandemic, a total of 30,194. Twitter messages in English were analyzed using the “nursing education” hashtag and keyword. All data cleaning and analysis were carried out with R software, and the tweet data set was analyzed using the frequency of keywords and sentiment analysis. Sentiment analysis of each tweet was conducted using various sentiment analysis dictionaries. The results showed that nursing, education, health, school, and nurses were the most used keywords. In the sentiment analysis conducted during the pandemic, 84 % of the tweets comprised positive, 12 % negative, and 4 % neutral sentiments. The conclusions highlight the importance of knowing and appreciating the contributions of nurses and nursing students during the pandemic and supporting more nurse professionals during crises such as the COVID-19 pandemic by addressing the problems during nursing education.

The Influence of Investor Sentiment on Scale Effect of the A-Share Market: An Empirical Analysis of Principal Components

Scale effect in the stock market refers to the negative correlation between company size and expected return, which is a common anomaly in the financial market. Investor sentiment is the opinion that investors create based on their expectations of the potential future cash flow from their assets and the inherent dangers of making investments. The initial goals of this paper were to develop an investor sentiment index system and investigate how it relates to the market scale impact. In this paper, principal component analysis and the CICSI index, which can better measure Chinese investor sentiment, are combined to construct investors More than 3000 sample stocks are grouped by size, the average return rate of each group is calculated, and the scale effect is tested. Through the verification of the scale effect under the optimistic, neutral, and pessimistic sentiment index, the applicability of generated sentiment index to the scale effect is confirmed.

Sentiment Analysis on Profit Management

This study aims to evaluate sentiments related to profit management practices using secondary data obtained from articles that have been published on the Scopus database. A qualitative approach is applied in this research methodology, with the utilization of SentiStrength software to classify sentiments. The results of the analysis show that positive sentiment dominates at 40% towards profit management, followed by neutral sentiment at 37%, and negative sentiment at 23%. Some of the positive aspects include improving economic welfare, investment and development, human resource development, and company competitiveness. On the other hand, negative issues related to profit management include exploitation of employees and natural resources, emphasis on profits without considering sustainability, ethical business practices, and possible social impacts. This research aims to present a comprehensive picture of sentiments towards for-profit management, covering its positive aspects, advantages, potential and benefits, while identifying potential weaknesses and threats associated with negative perceptions of for-profit management practices.

Performance of Machine Learning Models in Predicting Sentiments of Post-Covid Patients

With the widespread use of social media platforms, sentiment analysis of user-generated content has become a crucial task in understanding public opinion and trends. In this paper, we compare the performance of three popular machine learning models, namely Random Forest, Support Vector Machine (SVM), and Logistic Regression, in predicting sentiments of post-COVID patients on social media tweets. The study utilizes a dataset of labeled tweets representing positive, negative, and neutral sentiments. The preprocessing of textual data involves tokenization, stop-word removal, and conversion to lowercase to create a suitable input for the models. We utilize Term Frequency-Inverse Document Frequency (TF-IDF) vectorization to transform the text data into numerical features. The sentiment labels are converted to numeric representations for model training and evaluation. The three machine learning models are trained and evaluated on the dataset using metrics such as accuracy, precision, recall and F1-score. The evaluation results are presented and analyzed for each model, providing insights into their strengths and weaknesses in predicting sentiments. The experimental results demonstrate that Random Forest achieves the highest accuracy and F1-score, closely followed by SVM, while Logistic Regression performs slightly lower in comparison. However, all three models exhibit strong predictive capabilities, and their performances vary depending on the specific sentiment class. The findings provide valuable information for researchers and practitioners seeking to employ sentiment analysis in social media monitoring and other related applications. Overall, this study contributes to the understanding of the capabilities of Random Forest, SVM, and Logistic Regression models in sentiment analysis of social media tweets, and offers valuable insights for selecting the most suitable model for specific sentiment prediction tasks.

ASSESSING UNDERGRADUATES’ MISCONCEPTIONS ON CENTRAL DOGMA OF MOLECULAR BIOLOGY USING A 3-TIER DIAGNOSTIC TEST

Misconceptions can hinder students’ learning of biology, especially in the central dogma of molecular biology due to its connection with other topics. Studies have shown that Philippine high school students harbour significant misconceptions regarding genetics, including the central dogma. This study aims to develop a three-tier diagnostic test to identify misconceptions carried forward to undergraduate students enrolled in biologically related courses, leading to the development of the Central Dogma of Molecular Biology Questionnaire (CDMBQ). This study found that the CDMBQ has very good reliability (a = 0.88) and moderately positive construct validity (r = 0.4). It also revealed that the respondents have a low understanding of the central dogma (mean = 4.76), and they have acquired misconceptions pertaining to transcription, types of RNA, and translation. Lastly, perception items showed students have forgotten central dogma concepts, display confusion about the topic, and maintain neutral sentiments about their science teacher as well as have neutral feelings about their understanding of the central dogma. Nonetheless, they expressed interest in studying its concepts. These results confirm the reliability andvalidity of the CDMBQ for assessing misconceptions surrounding the central dogma of molecular biology.

SENTIMENT ANALYSIS OF INDONESIA'S CAPITAL CITY RELOCATION USING THREE ALGORITHMS: NAÏVE BAYES, KNN, AND RANDOM FOREST

The relocation of Indonesia's capital city from Jakarta to the IKN Nusantara on the island of Borneo has become a trending topic that triggers conversations and opinions on various social media. The pros and cons of this policy are very pronounced in various media, especially on Twitter or X platform. The purpose of this research is to conduct a public sentiment analysis of public opinion related to the relocation of Indonesia's capital city. Data is taken from tweets comments collected during a certain period from June to September 2023. This research uses a Natural Language Processing approach with data pre-processing techniques to prepare the data before applying labeling and classification algorithms. This research tests the accuracy of three algorithms used in classification, namely Naïve Bayes Classifier, K-Nearest Neighbor, and Random Forest. The results of the data classification show that positive sentiment has a value of 36.8%, neutral sentiment is at 25%, and negative sentiment related to the relocation of the capital city is 38.1%. Then an accuracy test was carried out on the Naïve Bayes Classifier Algorithm method which found an accuracy value of 65.26%, the K-Nearest Neighbor Algorithm of 58.25%, and the Random Forest Algorithm of 45.05%. This shows that the Naïve Bayes Classifier Algorithm method has better accuracy than other algorithms in predicting classification in sentiment analysis. This research also identifies the frequency of key words that often appear in each sentiment which can be valuable information for monitoring public opinion on social media.

A Comprehensive Analysis and Investigation of the Public Discourse on Twitter about Exoskeletons from 2017 to 2023

Exoskeletons have emerged as a vital technology in the last decade and a half, with diverse use cases in different domains. Even though several works related to the analysis of Tweets about emerging technologies exist, none of those works have focused on the analysis of Tweets about exoskeletons. The work of this paper aims to address this research gap by presenting multiple novel findings from a comprehensive analysis of about 150,000 Tweets about exoskeletons posted between May 2017 and May 2023. First, findings from temporal analysis of these Tweets reveal the specific months per year when a significantly higher volume of Tweets was posted and the time windows when the highest number of Tweets, the lowest number of Tweets, Tweets with the highest number of hashtags, and Tweets with the highest number of user mentions were posted. Second, the paper shows that there are statistically significant correlations between the number of Tweets posted per hour and the different characteristics of these Tweets. Third, the paper presents a multiple linear regression model to predict the number of Tweets posted per hour in terms of these characteristics of Tweets. The R2 score of this model was observed to be 0.9540. Fourth, the paper reports that the 10 most popular hashtags were #exoskeleton, #robotics, #iot, #technology, #tech, #innovation, #ai, #sci, #construction and #news. Fifth, sentiment analysis of these Tweets was performed, and the results show that the percentages of positive, neutral, and negative Tweets were 46.8%, 33.1%, and 20.1%, respectively. To add to this, in the Tweets that did not express a neutral sentiment, the sentiment of surprise was the most common sentiment. It was followed by sentiments of joy, disgust, sadness, fear, and anger, respectively. Furthermore, hashtag-specific sentiment analysis revealed several novel insights. For instance, for almost all the months in 2022, the usage of #ai in Tweets about exoskeletons was mainly associated with a positive sentiment. Sixth, lexicon-based approaches were used to detect possibly sarcastic Tweets and Tweets that contained news, and the results are presented. Finally, a comparison of positive Tweets, negative Tweets, neutral Tweets, possibly sarcastic Tweets, and Tweets that contained news is presented in terms of the different characteristic properties of these Tweets. The findings reveal multiple novel insights related to the similarities, variations, and trends of character count, hashtag usage, and user mentions in such Tweets during this time range.

Потребительские практики и настроения населения в условиях нестабильности 2020–2022 гг. (региональный аспект)

Various crises are integral for social development. Primarily crises manifest themselves in income and consumption changes, which makes consumer behavior and population sentiment studies necessary in unstable socio-economic conditions. The purpose of the study is to analyze consumer practice and population sentiment trends in the Vologda Oblast during the socio-economic changes of 2020–2022. The author determines that consumer practices of the region’s population hardly change in quantitative and qualitative terms, consumer sentiments also appear stable. Population’s assessment of capability for large purchases, car and housing purchases, savings remains neutral. However, the persistency of neutral consumer practices and sentiments levels suggests that the residents of the region do not expect positive changes in the economic life of their family and the country in the near future.

Investigating and Analyzing Self-Reporting of Long COVID on Twitter: Findings from Sentiment Analysis

This paper presents multiple novel findings from a comprehensive analysis of a dataset comprising 1,244,051 Tweets about Long COVID, posted on Twitter between 25 May 2020 and 31 January 2023. First, the analysis shows that the average number of Tweets per month wherein individuals self-reported Long COVID on Twitter was considerably high in 2022 as compared to the average number of Tweets per month in 2021. Second, findings from sentiment analysis using VADER show that the percentages of Tweets with positive, negative, and neutral sentiments were 43.1%, 42.7%, and 14.2%, respectively. To add to this, most of the Tweets with a positive sentiment, as well as most of the Tweets with a negative sentiment, were not highly polarized. Third, the result of tokenization indicates that the tweeting patterns (in terms of the number of tokens used) were similar for the positive and negative Tweets. Analysis of these results also shows that there was no direct relationship between the number of tokens used and the intensity of the sentiment expressed in these Tweets. Finally, a granular analysis of the sentiments showed that the emotion of sadness was expressed in most of these Tweets. It was followed by the emotions of fear, neutral, surprise, anger, joy, and disgust, respectively.