Twitter Mining Research Articles

Beyond Trisambodo Scandal: How Taxpayers’ Perception And Knowledge Influence Their Compliance

This study is aimed to predict and explain the impact of taxpayers' perceptions of the Directorate General of Taxes and tax knowledge, moderated by taxpayer income level, on tax compliance, particularly in the aftermath of the Rafael Alun Trisambodo scandal. A distinctive feature of this study is the employment of perceptions of the Directorate General of Taxes as an independent variable, which is innovatively derived from text mining Twitter data, alongside the application of ordinal data for the taxpayer income variable. Employing a survey methodology, this research engaged with a diverse cohort of 133 taxpayer respondents. The analytical framework adopted herein is the structural equation modeling analysis, which facilitates a comprehensive examination of the relationships between the specified variables. The findings reveal a significant causality between taxpayers' tax knowledge and their compliance behavior, positing that an enhanced understanding of tax-related matters invariably leads to greater adherence to tax obligations. This outcome underscores the imperative for the Directorate General of Taxes to intensify efforts in the realm of taxpayer socialization and education, aiming to augment levels of tax compliance. The insights gleaned from this study are anticipated to serve as valuable inputs for the Directorate General of Taxes in formulating strategies to bolster tax compliance among the populace.

Implementation of Text Mining in Socio-Economic Research

This work aims to analyze insights from social networks for identification of population satisfaction with pay level in Russia using the text mining approach. For this, a sentiment analysis framework was developed, which integrates Twitter mining tools and a sentiment index. Sentiments were extracted using Twitter mining and then recoded and substituted into the sentiment formula. The results of sentiment analysis indicate low satisfaction with levels of pay among Russians. Twitter was chosen as the object of research, as one of the most active and independent networks in Russia. It is possible that some of the tweets belong to authors who are not living in Russia at the moment, but their number is not significant and their interest in this issue, in the authors' opinion, only enhances the relevance of the problem under study.

Data mining twitter for COVID-19 sentiments concerning college online education

In the last decade there has been a large increase in corporate and public reliance on social media for information, rather than on the traditional news and information sources such as print and broadcast media. People freely express their views, moods, activities, likes/dislikes on social media about diverse topics. Rather than surveys and other structured data gathering methods, text data mining is now commonly used by businesses to go through their unstructured text in the form of emails, blogs, tweets, likes, etc. to find out how their customers feel about their company and their products/services. This paper reports upon a study using Twitter (recently renamed to “X”) data to determine if meaningful and actionable information could be gained from such social media data in regard to pandemic issues and how that information compares to a traditional survey. In early 2020, the COVID-19 pandemic hit and forced colleges to move classes to an online format. While there is considerable literature in regard to using social media to communicate geo-political issues and in particular pandemics, there is not a study using social media to explore public sentiment in regard to COVID’s forcing online education upon the public. In this study, text data mining was used to gain some insight into the feeling of Twitter users in regard to the effect of COVID-19 and the switch to online education in colleges. This study found that Twitter data mining did produce actionable information similar to the traditional survey, and the study is important since its results may influence organizations to explore the use of Twitter (and possibly other social media) to obtain people’s sentiments instead of (or in addition to) traditional surveys and other traditional means of gathering such information. This paper demonstrates both the process of text data mining social media and its application to current real-world issues.

CoMoSAOVA: Computational model for sentiment analysis and online visibility assessment

The online visibility of a brand, product or organization could influence customers’ decision to patronize it. Online reviews are opinions or emotions of customers that reveal their perception about the product over a period of time. The manual identification of features and sentiments toward an entity is a difficult task. In this study, a computational model was proposed to measure online visibility by mining Twitter data on discourse about a corporate entity – University of The Gambia. The numbers of Twitter posts, followers, followings, likes, retweets, quotes, replies and mentions serves as metrics for online visibility assessment. A linear regression evaluation between the age of the entity’s account and the number of its followers showed 96.81% correlation. This shows that the older an active Twitter account, the higher the chance of increasing its followers and its visibility. Another section of the model predicts the tweet sentiment of the entity’s followers with an accuracy of 93.68% using support vector machine and multilayer perceptron neural network. The computed average sentiment score of the case study was 0.3531996 based on Valence Aware Dictionary of sEntiment Reasoning (VADER) model. This means that positive sentiments were expressed in discussions on various issues where the entity was mentioned. The model will enable decision makers understand the sentiments expressed towards an entity. It also estimates online visibility of the entity based on its number of followers and the accounts’ lifespan. The perceived sentiments will aid better decisions that could advance loyalty to the entity. Future studies would examine other computational models to predict various Twitter features that increases an entity's online visibility.

Twitter Mining for Detecting Interest Trends on Biodiversity: Messages from Seven Language Communities

The recent rates of global change in nature are unprecedented in human history. The Intergovernmental Science-Policy Platform on Biodiversity and Ecosystem Services (IPBES) has proposed a framework to achieve transformative change. Transformative change with respect to nature will be driven by recognizing the values people have; making inclusive decisions based on these values; restructuring policies, rights, and regulations in accordance with them; and transforming social norms and goals that can drive change. Social media is a new source of information and a modern tool for monitoring public opinion on human–nature interactions. This study identified commonalities among seven language communities (the six official languages of the United Nations and the Japanese language), demonstrating the uniqueness of the Japanese community by comparing hashtags in tweets that include the term biodiversity and determining differences in interest and concern about biodiversity from the past to the present. Tweets accessible at the end of 2021 that focus on biodiversity were collected from the Twitter server and used to form a text dataset. Interest was then qualitatively and quantitatively identified using natural language processing technology. Engagements and diversity indices were found to be on the rise in all language communities. We found that the Japanese language community has a different perspective on the relationship between biodiversity and humans from the scope of the IPBES conceptual framework. Future work should examine the relationship between passion for biodiversity and the Sustainable Development Goals. In addition, collaboration with various people around the world is necessary to understand the concept of biodiversity in different traditions and cultures.

Pooches on a platform: Text mining twitter for sector perceptions of dogs during a global pandemic.

Businesses commonly text mine Twitter data to identify patterns and extract valuable information. However, this method is rarely applied to the animal welfare sector. Here, we describe Twitter conversations regarding dogs during a global pandemic, assess the evolution of sentiment, and examine the dynamics of sector influence. Between March and August 2020, we gathered 61,088 unique tweets from the United Kingdom and Republic of Ireland, relating to COVID-19 and dogs. Tweets were assigned to one of four pandemic phases and active accounts were assigned to a sector: Personal (i.e., UK and ROI public), Press (i.e., mass media), State (i.e., Government, Police, and NHS), and Other (i.e., welfare organizations, social enterprises, research organizations, charity, and business). Word frequency and sentiment analysis between phases and sectors were assessed, and cross correlation functions and lagged regressions were used to evaluate sector influence. Topical foci of conversations included: meat trade, separation anxiety and dog theft. Sentiment score remained stable until the last phase where sentiment decreased (F 3, 78, 508 = 44.4, p < 0.001), representing an increased use of negative language. Sentiment differed between the four sectors (F 3, 11, 794 = 52.2, p < 0.001), with Personal and Press accounts presenting the greatest use of negative language. Personal accounts were initially partly influenced by State accounts (R = -0.26; p = 0.05), however this altered to Press accounts by the last phase (R = -0.31; p = 0.02). Our findings highlight that whilst Personal accounts may affect sector-specific messaging online, perhaps more importantly: language used, and sentiment expressed by Press, State and Other accounts may influence public perception. This draws attention to the importance of sector responsibility regarding accurate and appropriate messaging, as irresponsible/ill-considered comments or campaigns may impact future human-animal interaction.

New Higher Education Policy and Strategic Plan: Commensurate India’s Higher Education in Global Perspective

A national education policy (NEP) is a comprehensive framework to guide education development in any country. In light of this, the present contribution is structured on an analysis of recent changes in the education policy of an emerging economy. The study is an original contribution to the qualitative study literature, applying the system model of inquiry and Twitter mining methodology using NVIVO 12 software. The sketch of the article begins by analysing the limitations and gaps of the extant education policy in an emerging country, and its implications through the SAP-LAP framework, and then analysing the reaction of various stakeholders on Twitter. The sentiment index (SI) scored +3.59, denoting a broad approval of the policy amongst the people. Further, the gap analysis develops the pathway to learning issues that guide the recommendations. The article concludes by offering a capacity development framework for better implementation and monitoring of new education policies for lower-middle income countries.

Large-Scale Twitter Mining for Extracting the Psychological Impacts of COVID-19

Large-Scale Twitter Mining for Extracting the Psychological Impacts of COVID-19

Heterogeneous Feature Analysis on Twitter Data Set for Identification of Spam Messages

Spam is an undesirable content that present on online social networking sites, while spammers are the users who post this content on social networking sites. Unwanted messages posted on Twitter may have several goals and the spam tweets can interfere with statistics presented by Twitter mining tools and squander users’ attention.. Since Twitter has achieved a lot of attractiveness through-out the world, the interest towards it by the spammers and malevolent users is also increases. To overcome the spam problems many researchers proposed ideas using machine learning algorithms for the identification of spam messages. Not only the selection of classifiers but also the variegated feature analysis is essential for the identification of irrelevant messages in social networks. The proposed model performs a heterogeneous feature analysis on the twitter data streams for classifying the unsolicited messages using binary and continuous feature extraction with sentiment analysis on social network datasets. The features created are assessed using significant stratagems and the finest features are selected. A classifier model is built using these feature vectors to predict and identify the spam messages in Twitter. The experimental results clearly show that the proposed Sentiment Analysis based Binary and Continuous Feature Extraction model with Random Forest (SA-BC-RF) approach classifies the spam messages from the social networks with an accuracy of 90.72% when compared with the other state-of-the-art methods.

Multi-Layer Classification and Segmentation with Opinion Mining Learning Ensemble

Social media has become the main area for advertising, events, campaigns, protests etc. in recent years. It offers the public a forum for expressing their opinions and beliefs to the masses. The user beliefs, habits and interests of businesses are extremely important and give users a glimpse into their thinking. Data mining is one of the tools that enables these businesses to extract useful information from user data that can be examined to generate a set of knowledge and identify a user opinion that helps companies to create user-specific products. Twitter Data Mining and other social platforms are very important since its enormous user base consists of a mixture of thoughts and opinions that may be used to anticipate results of campaigns, product assessments and similarity if correctly studied. This research provides a classification system to perform Twitter Opinion Mining Segmentation based on Ensemble Learning. The suggested approach can detect and filter out boxes and uses text segmentation for efficient text classification and voice taging.

Enhancing Event Descriptions through Twitter Mining

We describe a simple IR approach for linking news about events, detected by an event extraction system, to messages from Twitter (tweets). In particular, we explore several methods for creating event-specific queries for Twitter and provide a quantitative and qualitative evaluation of the relevance and usefulness of the information obtained from the tweets. We showed that methods based on utilization of word co-occurrence clustering, domain-specific keywords and named entity recognition improve the performance with respect to a basic approach.

You Are What You Tweet: Analyzing Twitter for Public Health

Analyzing user messages in social media can measure different population characteristics, including public health measures. For example, recent work has correlated Twitter messages with influenza rates in the United States; but this has largely been the extent of mining Twitter for public health. In this work, we consider a broader range of public health applications for Twitter. We apply the recently introduced Ailment Topic Aspect Model to over one and a half million health related tweets and discover mentions of over a dozen ailments, including allergies, obesity and insomnia. We introduce extensions to incorporate prior knowledge into this model and apply it to several tasks: tracking illnesses over times (syndromic surveillance), measuring behavioral risk factors, localizing illnesses by geographic region, and analyzing symptoms and medication usage. We show quantitative correlations with public health data and qualitative evaluations of model output. Our results suggest that Twitter has broad applicability for public health research.

Impact of COVID 19 on Indian Migrant Workers: Decoding Twitter Data by Text Mining.

The Coronavirus pandemic has induced a huge economic crisis. The norms of social distancing and consequent lockdown to flatten the curve of this infection has brought economic activity across the globe to a standstill. A mass exodus of workers from major urban centres of India to their native villages started. Mental, financial and emotional agony inflicted due to job-loss, lack of job and livelihood opportunities led to this. A massive macroeconomic crisis for the country with serious ramifications has consequently exploded. The present study explores and captures the diffusion and discovery of information about the various facets of reverse migration in India using Twitter mining. Tweets provide extensive opportunities to extract social perceptions and insights relevant to migration of workers. The massive Twitter data were analysed by applying text mining technique and sentiment analysis. The results of the analysis highlight five major themes. The sentiment analysis confirms the confidence and trust in the minds of masses about tiding through this crisis with government support. The study brings out the major macroeconomic ramifications of this reverse migration. The study’s findings indicate that a concentrated joint intervention by the State and Central Governments is critical for successfully tiding through this crisis and restoring normalcy. The subsequent policy measures announced by the government are being critically gauged. In addition, the authors have proposed measures to ameliorate this damage on the formal and informal sectors.

An Empirical Study on Customer Churn Behaviours Prediction Using Arabic Twitter Mining Approach

With the rising growth of the telecommunication industry, the customer churn problem has grown in significance as well. One of the most critical challenges in the data and voice telecommunication service industry is retaining customers, thus reducing customer churn by increasing customer satisfaction. Telecom companies have depended on historical customer data to measure customer churn. However, historical data does not reveal current customer satisfaction or future likeliness to switch between telecom companies. The related research reveals that many studies have focused on developing churner prediction models based on historical data. These models face delay issues and lack timelines for targeting customers in real-time. In addition, these models lack the ability to tap into Arabic language social media for real-time analysis. As a result, the design of a customer churn model based on real-time analytics is needed. Therefore, this study offers a new approach to using social media mining to predict customer churn in the telecommunication field. This represents the first work using Arabic Twitter mining to predict churn in Saudi Telecom companies. The newly proposed method proved its efficiency based on various standard metrics and based on a comparison with the ground-truth actual outcomes provided by a telecom company.

Real-Time Brand Reputation Tracking Using Social Media

How can we know what stakeholders think and feel about brands in real time and over time? Most brand reputation measures are at the aggregate level (e.g., the Interbrand “Best Global Brands” list) or rely on customer brand perception surveys on a periodical basis (e.g., the Y&amp;R Brand Asset Valuator). To answer this question, brand reputation measures must capture the voice of the stakeholders (not just ratings on brand attributes), reflect important brand events in real time, and connect to a brand’s financial value to the firm. This article develops a new social media–based brand reputation tracker by mining Twitter comments for the world’s top 100 brands using Rust–Zeithaml–Lemon’s value–brand–relationship framework, on a weekly, monthly, and quarterly basis. The article demonstrates that brand reputation can be monitored in real time and longitudinally, managed by leveraging the reciprocal and virtuous relationships between the drivers, and connected to firm financial performance. The resulting measures are housed in an online longitudinal database and may be accessed by brand reputation researchers.

Mining Twitter to Detect Hotspots in Psychology

Abstract. For identifying psychological hotspot topics, a mere focus on bibliometric data suffers from a publication delay. To overcome this issue, we introduce Twitter mining of ongoing online communication among scientists for the detection of psychological research topics. Specifically, we collected the entire 69,963 tweets posted between August 2007 and July 2020 from 139 accounts of psychology professors, departments, and research institutes from the German-speaking countries, as well as sections of the German Psychological Society (DGPs). To examine whether Twitter topics are hotspots in terms of indicating future publication trends, 346,361 references in the PSYNDEX database were extracted. For determining the additional value of our approach in contrast to traditional conference analysis, we gathered all available conference programs of the DGPs and its sections since 2010 and compared dates of topic emergence. Results revealed 21 topics addressing societal issues (e.g., COVID-19), methodology (e.g., machine learning), scientific research (e.g., replication crisis), and different areas of psychological research. Ten topics indicated an increasing publication trend, particularly topics related to methodology or scientific transparency. Seven Twitter topics emerged earlier on Twitter than at conferences. A total of four topics could be expected neither by bibliometric forecasting nor conference contents: “methodological issues in meta-analyses”, “playfulness”, “preregistration”, and “mobile brain/body imaging”. Taken together, Twitter mining is a worthwhile endeavor for identifying psychological hotspot topics, especially regarding societal issues, novel research methods, and research transparency in psychology. In order to get the most comprehensive picture of research hotspots, Twitter mining is recommended in addition to bibliometric analyses of publication trends and monitoring of conference topics.

Mapping of the Covid-19 Vaccine Uptake Determinants From Mining Twitter Data.

Opinion polls on vaccine uptake clearly show that Covid-19 vaccine hesitancy is increasing worldwide. Thus, reaching herd immunity not only depends on the efficacy of the vaccine itself, but also on overcoming this hesitancy of uptake in the population. In this study, we revealed the determinants regarding vaccination directly from people’s opinions on Twitter, based on the framework of the 6As taxonomy. Covid-19 vaccine acceptance depends mostly on the characteristics of new vaccines (i.e. their safety, side effects, effectiveness, etc.), and the national vaccination strategy (i.e. immunization schedules, quantities of vaccination points and their localization, etc.), which should focus on increasing citizens’ awareness, among various other factors. The results of this study point to areas for potentially improving mass campaigns of Covid-19 immunization to increase vaccine uptake and its coverage and also provide insight into possible directions of future research.

Service quality monitoring in confined spaces through mining Twitter data

Promoting public transport depends on adapting effective tools for concurrent monitoring of perceived service quality. Social media feeds, in general, provide an opportunity to ubiquitously look for service quality events, but when applied to confined geographic area such as a transport node, the sparsity of concurrent social media data leads to two major challenges. Both the limited number of social media messages--leading to biased machine-learning--and the capturing of bursty events in the study period considerably reduce the effectiveness of general event detection methods. In contrast to previous work and to face these challenges, this paper presents a hybrid solution based on a novel fine-tuned BERT language model and aspect-based sentiment analysis. BERT enables extracting aspects from a limited context, where traditional methods such as topic modeling and word embedding fail. Moreover, leveraging aspect-based sentiment analysis improves the sensitivity of event detection. Finally, the efficacy of event detection is further improved by proposing a statistical approach to combine frequency-based and sentiment-based solutions. Experiments on a real-world case study demonstrate that the proposed solution improves the effectiveness of event detection compared to state-of-the-art approaches.

Mining twitter to explore the emergence of COVID-19 symptoms.

The Centers for Disease Control and Prevention (CDC) in United States initially alerted the public to three COVID-19 signs and symptoms-fever, dry cough, and shortness of breath. Concurrent social media posts reflected a wider range of symptoms of COVID-19 besides these three symptoms. Because social media data have a potential application in the early identification novel virus symptoms, this study aimed to explore what symptoms mentioned in COVID-19-related social media posts during the early stages of the pandemic. We collected COVID-19-related Twitter tweets posted in English language between March 30, 2020 and April 19, 2020 using search terms of COVID-19 synonyms and three common COVID-19 symptoms suggested by the CDC in March. Only unique tweets were extracted for analysis of symptom terms. A total of 36 symptoms were extracted from 30,732 unique tweets. All the symptoms suggested by the CDC for COVID-19 screening in March, April, and May were mentioned in tweets posted during the early stages of the pandemic. The findings of this study revealed that many COVID-19-related symptoms mentioned in Twitter tweets earlier than the announcement by the CDC. Monitoring social media data is a promising approach to public health surveillance.

Exploration of Opinion from Twitter Data

To share information nowadays, people use social media sites from all around the world. For example, Twitter is a social media site enable users with facilities like reading, sending post recognized as ‘tweets’ and interrelate with diverse peoples. People often post their sentiments about their day-to-day lives, the whole thing for example places and brands. Businesses makes profit from this vast social media site by gathering data related to sentiments of people. Presenting a model that can accomplish opinion analysis on collected data from Twitter is the aim of this paper. To analyze highly unstructured and unorganized data in Twitter makes it difficult to manage and use. In our proposed model we are combining the work of unsupervised and supervised algorithms. Extracting and classifying each tweet depending on its opinion considered to be a neutral, positive or negative. Zomato and Swiggy are the two subjects about which data were collected to show which online food delivery business has more popularity. We have used diverse machine learning algorithms for testing. Testing metrics like f-score and cross validation were used for testing the result from these models. Our model has shown performance which is considered to be robust on directly mining Twitter texts.