Machine Learning-Based Sentiment Analysis Towards Indian Ministry

Long before the elections were held, the topic related to elections was widely discussed on news portals and social media, including Twitter. A few studies related to the Indonesian election have tried to predict candidates who will run for the presidential election, but there has been no research that examines public sentiment on social media towards each of the potential candidates. The main objective of this study is to analyze the public sentiment in Twitter towards potential candidates for the 2024 Indonesian presidential election. This research seeks to fill the gaps in previous research and become a reference for further research regarding sentiment analysis for election prediction using Twitter. The presidential candidates used in the research are the top 3 candidates based on the Poltracking survey, namely Ganjar Pranowo, Prabowo Subianto, and Anies Baswedan. The data were taken from January until October 2022, more than a year before the general election began. To predict the sentiment, four different machine-learning methods were used and compared to each other. There are Naïve Bayes, Support Vector Machines, Random Forests, and Neural Networks. Based on the sentiment results of each candidate, the highest sentiment towards Prabowo is neutral (55.49%), the highest sentiment towards Ganjar is positive (61.34%), and the highest sentiment towards Anies is neutral (44.84%). Results from the study also show that Anies was the presidential candidate who received more negative sentiment than the other two (56.63%). Meanwhile, Ganjar Pranowo got the most positive sentiment of all (42,69%). For the neutral sentiment, Anies Baswedan also got the most results (39,87%), followed by Prabowo (38.99%) and Ganjar Pranowo (21.14%). The result of the study also discovered that random forest and neural networks have the best performance for sentiment analysis.

Aim: Coronary illness is one of the main sources of mortality in this current world. A basic test in the field of clinical information assessment is the expectation of cardiovascular infection. The fundamental target of this paper is to work on the exactness of the Data mining algorithms being used to improve heart disease prediction. We will be comparing the novel Random forest with K Nearest Neighbor to find out which of these can give us the best accuracy. Material and Methods: The study used 98 samples with Novel Random Forest and K Nearest Neighbor is executed with varying training and testing splits for predicting the accuracy for heart disease prediction with the 80% of G-power value and data about cardiovascular disease was gathered from numerous web sources, including latest research findings and threshold 0.05%, confidence interval 95% mean and standard deviation. The performance of the accuracy rate of the classifiers is examined using the heart disease dataset.. There was a statistical insignificant difference among Innovative Random Forest and K Nearest Neighbor p = 0.484 (p>0.05). Results and Discussion: The accuracy of predicting heart disease in Novel Random Forest 90.16% and K Nearest Neighbor 67.21% is obtained. Conclusion: Prediction of Heart disease using the innovative Random Forest (RF) technique appears to be a significant improvement over the K Nearest Neighbor (KNN) algorithm in terms of accuracy.

Citation (2023), "Index", Tyagi, P., Grima, S., Sood, K., Balamurugan, B., Özen, E. and Eleftherios, T. (Ed.) Smart Analytics, Artificial Intelligence and Sustainable Performance Management in a Global Digitalised Economy (Contemporary Studies in Economic and Financial Analysis, Vol. 110B), Emerald Publishing Limited, Bingley, pp. 265-276. https://doi.org/10.1108/S1569-37592023000110B018 Publisher: Emerald Publishing Limited Copyright © 2023 Pallavi Tyagi, Simon Grima, Kiran Sood, B. Balamurugan, Ercan Özen, and Thalassinos Eleftherios INDEX Accounting, 146 Actual economic activity, 175 Administrative security controls in SME, current state of, 35–37 Africa, effect of COVID-19 debt accumulation, 165 Agriculture, 133 Alternative finance models, 102 Amazon (technology company), 98 Annual appraisals, 252 Anti-black Money Act (2015), 126 Anti-money laundering (AML), 60, 172 Apple (technology company), 98 Artificial intelligence (AI), 23, 85–86, 172, 217, 244, 252–253 ability of AI and SA to improve PM systems, 257 application of AI and SA in business processes, 255 automating PM Systems, 259–261 in business processes, 255–256 classification models to predict employee performance, 257–259 classification of AI, based on capabilities, 253–254 classification of AI, based on functionality, 254 competition, 219 demographics of customers, 219 drivers of digitisation and AI in retail, 218 in HR management, 259 limitations of AI and SA in PM systems, 261–262 for mapping cybersecurity controls for SME, 46–48 in PM systems, 257 retail customers, 218–219 retail digitisation using, 219–220 super, 254 technology and, 218 types, 253 Aspirational Districts Programme, The, 88 Asset management segment, 99 Augmented reality, 23 Authors’ network analysis, citation as per, 68–69 Autonomous robotics, 23 Balance sheet lending (BSL), 100 Bank 4.00, 102 Bank of Baroda, 7, 11–12 Bank of Hindustan, 2 Banking, 2, 98, 206 co-operative banks, 2 commercial banks, 2 industry, 205 payments banks, 2 small finance banks, 2 Banking, financial services, and insurance (BFSI), 29 Banking Regulation Act (1949), 2 Banks, 205 Bibexcel, 135 Bibliometrics, 57, 60 analysis, 141 of entrepreneurial universities, 57 R Package, 135 research, 141 Bibliometrix, 178 Biblioshiny, 178 Big data, 23, 85, 255 analytics, 84 BigTechs, 101 Billion Prices Project, 87 Black box model, 85 Black money, 58–59 Blending data sciences in economic and social issues, 86–87 Blockchain, 132 content analysis, 137–141 data analysis, 135–137 directions for future research, 141–142 implications, 141 methodology, 133–134 technology, 132 Bombay Stock Exchange (BSE), 75–76 Bootstrapping methods, 227 Bring your own device policy (BYOD policy), 40 Business domain-wise mission critical asset security (Business DMCAS), 43–44 Business to-Person lending models (B2P lending models), 101 Business-to-Business lending models (B2B lending models), 101 Businesses, 230 AI in, 255–256 changing priorities of CIA triad based on business domain, 30–31 SA in, 256–257 Buy Now Pay Later (BNPL), 101 C4.5 decision tree, 258 Canara Bank, 7, 9–10, 18 Capability maturity model (CMM), 26 Cashkumar (P2P lending platform), 107 version 2. 0, 108 Cashkumar Peer-to-Peer Lending Platform (Cashkumar P2P Lending Platform), 107–108 digital lending, 100–107 emotional analysis, 116–117 FinTech, 98–100, 108–109 literature review, 108 negative reviews, 119–120 P2P lending, 109–111 positive reviews, 118–119 research methodology, 112 sentiment analysis perspective, 111–112 theoretical background, 107 Castle approach, 28 Casual conversations, 250 Central Bank, 193 Central bank digital currency (CBDC), 190 Central Bank of Nigeria, 190 CIA triad assess priority of CIA triad for DMCA, 43 changing priorities of CIA triad based on business domain, 30–31 CIA trinity, 27 Citation network analysis, 67–68 citation as per authors’ network analysis, 68–69 Cloud computing, 23, 86 Co-authorship analysis, 60 Co-authorship network analysis as authors on money laundering, 62–66 as countries, 64–66 Co-occurrences analysis, 60 of keywords analysis on money laundering, 66–69 network analysis on money laundering, 66 Co-operative banks, 2, 4 Commercial banking, 2 Commercial banks, 2 foreign banks, 3 private sector banks, 3 public sector banks, 3 RRBs, 3 Communications service providers, 101 Companies Act, 105 Competitive pressure, 229 Conceptual model constructs and items measured, 221–223 development of, 221 Conceptual research model, 221 Confidence interval (CI), 227 Consumers, 216 Consumption of goods and services, 22 Content analysis, 137, 179 digitisation of agriculture, 140 supply chain management, 140 sustainable economic development, 140–141 Cooperative savings, 59 Cooperative Societies Act (1912), 4 Core cybersecurity concepts, 26–31 changing priorities of CIA triad based on business domain, 30–31 CIA Triad, 27 Defence in Depth, 28–29 DMCA, 29–30 Coronavirus, 162 Corporation threat agents, 24 Corruption, 56, 124 Cost-benefit analysis, 84 COVID 19, 5, 218 Africa, 165 effect of COVID-19 debt accumulation, 164 debt crisis, 164 debt statistics, 162–164 Europe, 164–165 global debt crisis, 161 heavily indebted countries, 167–168 and Indian Banking, 5 literature review, 161–162 methodology, 161 multilateral organisations, 166–167 pandemic, 160, 234–235 rich countries, 165–166 solution to overcome, 165 Cross industry standard process for data mining (CRISP-DM), 257 Crowdfunding, 99–100 Cryptocurrencies, 98 Customer relationship management (CRM), 253 Customers, 229 demographics of, 219 screening process, 58 Cutting-edge technology, 58 Cyber assets, 27 Cyber risk, 23 Cyberattacks faced by SMEs, experience of, 39–40 Cybercrime, 56 Cybercriminals, 37, 40 Cybersecurity, 23 calculate SME’s minimum overall cybersecurity controls implementation level, 44–45 implement prioritised cybersecurity controls for Business DMCAS, 43–44 responsible AI for mapping cybersecurity controls for SME, 46–48 Cybersecurity framework (CSF), 25 Cyberspace, 23 Data analysis, 224 measurement model, 224–226 structural model, 226–229 test, 224 tool, 88 Data collection, 223–224 Data extraction, 134 Data lags, 91–92 Data localisation problem, 92 Data mining, 85 techniques, 90 Data privacy and security, 91 Data science, 86 techniques, 85 Data-driven policy, India’s stance on, 87–89 Debt crisis, 161, 164 Debt restructuring, 162 Debt Service Suspension Initiative (DSSI), 166 Debt statistics, 162 external debt stocks, 162–163 massive spending by richer countries, 163–164 sovereign default, 164 Decision Tree, 257 Decision-making management, 173 Defence in depth (DiD), 28 Delay payments, 204 Democratisation of opinions, 236 Descriptive analysis, 60 Desktops, 40 Digital circuits, 22 Digital government, 87 Digital India campaigns, 89 Digital lending, 100 alternative finance models, 102 ecosystem, 100–102 functional business models in India, 105–107 funds transfer mechanism as per RBI guidelines, 105 global scenario, 101 governing enactments, 104–105 India, 102 landscape, 102–104 market share, 102 Digital sentiments, 236 Digital technologies, 109 Digital transformation, 216 in agriculture, 141 Digitalisation process of banking industry, 6 Digitisation intelligence competition, 219 demographics of customers, 219 drivers of digitisation and AI in retail, 218 retail customers, 218–219 technology and AI, 218 Digitisation of agriculture, 133, 140 Digitisation transforms retailing exchanges, 220 Directorate of Enforcement (ED), 126 Dirty money, 124 Document-term matrix (DTM), 178 Domain-wise Least Cybersecurity Implementation Framework (DLCI Framework), 41 assess priority of CIA triad for DMCA, 43 calculate SME’s DLCI Level, 45–46 calculate SME’s DMCAS Level, 44 calculate SME’s minimum overall cybersecurity controls implementation level, 44–45 identify DMCA, 41–43 implement prioritised cybersecurity controls for business DMCAS, 43–44 responsible AI for mapping cybersecurity controls for SME, 46–48 WCCI for SME, 44 Domain-wise Mission Critical Asset (DMCA), 29–30 Domestic lending by banks, 205 Drug trafficking, 56 e-CNY, 192 E-commerce platforms, 101 sites, 216 Earnings management, 146 conceptual framework, 147 income-targeting approach, 150–151 literature review, 148–150 priority theory of sustainable finance, 147–148 surplus income model, 152–155 surplus income model for sustainability, 151–152 Econometric models, 84 Economic and financial performance in topic modelling framework, relationship between money laundering and, 184–185 Economic growth (EG), 125, 128, 161, 173, 201 Electric vehicles infrastructure, investment target for, 202 Electronic word of mouth (e-WOM), 235 Embed quality assurance, 47 Emotion Lexicon (EmoLEX), 111 Emotional analysis, 116–117 Emotions, 116 Employees, 245, 258 in India, 175 narrow assessment of, 252 performance, 245 threat agents, 24 eNaira, 190, 193–195 CBDC, 190 money, 190 performs, 190 speed wallet, 196 Environmental, social and governance (ESG), 76, 79–81 ESG-based socially responsible investments, 75 Indian investors looking for, 75–76 Environmental accounting, 149 Environmental reporting, 146 Europe, effect of COVID-19 debt accumulation, 164–165 European Central Bank (ECB), 162 External debt stocks, 162–163 External incentives, 154 External stakeholders, 248 Facebook (technology company), 98 Federal Bank, 7, 13–14, 18 Finance models, 102 Financial Action Task Force (FATF), 58, 125 Financial crimes action plan for resolving financial crimes using SRI–ESG model, 81 channel for, 77–78 effects of, 79 terrorism financing devastating part of, 78–79 impact of unethical investments on, 79 Financial crisis (2008), 98 Financial industry, 205 Financial institutions, 205 in achieving sustainable economic goals, 206–207 through priority sector lending, 208–210 Financial markets, 101, 104 Financial performance Bank of Baroda, 11–12 Canara Bank, 9–10 co-operative banks, 4 COVID 19 and Indian Banking, 5 COVID 19, 5 data analysis, 8 data collection, 7 Federal Bank, 13–14 findings, 17–18 foreign banks, 3 HDFC Bank, 14–15 hypothesis testing for net profit, 16–17 hypothesis testing for NPA, 17 ICICI Bank, 12–13 Indian Bank, 10–11 limitation of study, 8 literature review, 5–7 non-performing assets, 4 non-scheduled banks, 4 payments banks, 4 private sector banks, 3 public sector banks, 3 research methodology, 7 research methodology, 8 research objectives, 7 RRB, 3 sample frame, 7 schedule banks, 4 small finance banks, 3–4 in topic modelling framework, relationship between money laundering and economic and, 184–185 Union Bank, 10 Yes Bank, 15–16 Financial services, 98 Financial study, 58 Financial Technology (FinTech), 98 branches of FinTech Industry, 99–100 classified into the following types, 98–99 credit, 102 landscape, 99 lenders, 101 start-ups, 109 Financing segment, 99 Firms, 147 Five-year planning process, 87 Forecasting methods, 84 Foreign Banks, 3 Formal process in PM systems, 249–250 Fugitive Economic Offenders Act (2018), 126 Functional business models in India, 105–107 Funds transfer mechanism as per RBI guidelines, 105 Global economy, 160 Global reporting initiative (GRI), 149 Globalisation of economies, 124 Gold medal, 238 Goods and Service Tax, 126 Google (Private companies), 91, 98 reviews, 114 Governance in India, 87 reporting, 146 Grameen Foundation, The, 87 Green accounting, 149 Green banking assessing funding needed by international agency, 205 investment target for electric vehicles infrastructure, 202 investment target for renewable energy generation, 201–202 investment target to set up smart cities, 203–204 methodology, 206 results, 206 role of financial institutions in achieving sustainable economic goals, 206–207 role of financial institutions through priority sector lending, 208–210 Green development, 210 Green energy, 210 Green growth, 206 Gross domestic product (GDP), 160, 174, 205 HDFC Bank, 7, 14–15, 18 Human bias, 252 Human resources (HR), 172, 255 AI in HR management, 259 Human-based PM systems, 252 Hume’s Aesthetic Theory, 108 Hypothesis testing for net profit, 16–17 for NPA, 17 ICICI Bank, 7, 12–13, 18 ID3 decision tree, 258 Illicit drug trafficking, 59 IMF Fact Sheet, 125 Income smoothing, 151 Income-targeting approach, 150–151 Incremental approach, 84 India current market trend of, 74–75 digital lending, 102 functional business models in, 105–107 measurements to control money laundering terror funding in, 125–126 retail scenario in, 217–218 SRI in, 75 stance on data-driven policy, 87–89 Indian Bank, 7, 10–11 Indian banking industry, 4 sector, 2 Indian Economy future implication of study, 128 impacts of money laundering on, 126–127 impacts of terror financing on, 127–128 measurements to control money laundering terror funding in India, 125–126 nexus of money laundering and terrorism financing, 125 Indian government, 90 Indian investors looking for ESG Investments, 75–76 Industry 1.0, 22 Industry 2.0, 22 Industry 4.0 digitisation, 23 Inferential research approach, 223 Informal economy, 174 Informal process in PM systems, 250 Information and communications technologies (ICTs), 23, 88, 217 assets, 27 Information security, 27 Information security management system (ISMS), 24 Information technology, 124 Institute for Energy Economics and Financial Analysis (IEEFA), 201 Insurance, 98 Intangible assets, 27 Integration of economies, 124 Interest-bearing eNaira, 194–195 Internal stakeholders, 248 International agency, assessing funding needed by, 205 International Energy Agency (IEA), 205 International Monetary Fund (IMF), 163, 175 International Standards Organization, 260 Internet of Things (IoT), 23, 84, 86, 255 Investment, 98 management, 175 target for electric vehicles infrastructure, 202 target for renewable energy generation, 201–202 target to set up smart cities, 203–204 IP Act (2000), 91 Keynesian model, 193 Know Your Customer (KYC), 106 Knowledge management cybersecurity, 40 Laptops, 40 Latent Dirichlet allocation (LDA), 179 Lender’s Club, 110 Lending policies, 205 Lending practices, 206 Link strength, 137 Logical controls, 35 Machine learning (ML), 86, 257 Malware assaults, 39 Management accounting, 148 Managerial discretion, 147 Managers and employees, 245–246 Market share, 102 Marketers, 218 Marketplace lending (MPL), 100 Massive data analysis approach, 59 Measurement model of data analysis, 224–226 Medal, 238 Mendeley database, 133 Mentor–Protege relationship, 250 Micro, small and medium enterprises (MSMEs), 208 Microsoft (Private companies), 91 Minerals, 30 Mission critical assets, 29 MIT Sloan School of Management, 87 Modern banking, 2 Money, 56 Money laundering, 60, 79, 124, 172–173 analysis of word cloud, 181 annual trend of publication, 61 citation network analysis, 67–69 co-authorship network analysis, 62 co-authorship network analysis as authors on, 62 co-authorship network analysis as countries, 64–66 co-occurrences network analysis on, 66–67 countries analysis, 62 data and methodology, 175–179 descriptive analysis, 179–180 historical background of, 58–60 impacts of money laundering on Indian economy, 126–127 investigating TF-IDF, 182–184 link between words, 181 literature review, 173–175 measurements to control money laundering terror funding in India, 125–126 nexus of, 125 relationship between money laundering and economic and financial performance in topic modelling framework, 184–185 research methodology and data, 60 results, 61 sources analysis, 61–62 Money lending, old concept of, 100 Mordor Intelligence, 89 Naïve Bayes classifiers, 258 Narcotic Drugs and Psychotropic Substances Act (NDPS), 59 NASSCOM, 89 National Association of Securities Dealer Automated Quotations, The, 98 National Strategy for Artificial Intelligence by NITI Aayog, 88 Natural catastrophes, 24, 34 Natural disasters, 34 Neo banks, 101 Net profit, hypothesis testing for, 16–17 Netnograhphy, 236 Nigeria CBDC, 190 current features of, 193–194 interest-bearing eNaira, 194–195 literature review, 191–193 no transaction costs, 195 redesigning, 194 security, 195–196 NIRAMAI, 88 NIST, 25 NITI Aayog, 88 Non-banking financial corporations (NBFCs), 100, 206 Non-performing Assets, 4 Non-performing loans (NPL), 162 Non-scheduled banks, 2, 4 Normalisation, 178 NPA, hypothesis testing for, 17 Offline P2P lending, 100 Olympic Games Tokyo (2020), 237 Olympics, 240 destination, 234 players, 239 Online P2P lending platforms, 100, 109–110 Online platforms, 40 Opaque system, 252 Open Government Data (OGD), 87 Opensource Stack software, 87 Oracle (Private companies), 91 Organisation-owned devices, 40 Organisational goals, 246 Organisations, 244 Organised retailers, 230 Organised retailing, 221, 223 Palantir Technologies (American software company), 87 Pandemic, 160 Parallel economy, 124 Partial least square (PLS), 224 Payment, 191 Payments Banks, 2, 4 Performance appraisal (PA), 244 Performance assessments, 249 Performance improvement, notifications of, 249–250 Performance management systems, 244–245 AI and SA, 252–257 AI and SA in PM systems, 257–262 components of, 245–246 formal processes, 249–250 informal processes, 250 inputs to PM systems, 250–251 issues in current PM systems, 251–252 monitoring, 246–247 outputs from PM systems, 251 planning, 246 principles of PM systems, 248–249 processes in PM systems, 249 reviewing, 247 rewarding, 247 stakeholders in PM systems, 247–248 tasks in PM Systems, 246 Person-to-Business lending models (P2B lending models), 101 Person-to-Person lending models (P2P lending models), 101, 109–111 crediting, 109 elements, 100 lending platforms, 100–101, 106 lending services, 104 Physical retailers, 216 Physical security current state of physical security controls in SME, 34 measures, 34 Physical stores, 217 Planning–programming–budgeting system, 84 Platform lending, 100 Policy-making process, 84 in India, 87 Predictive modelling techniques, 85 Prevention of Money Laundering Act (PMLA), 59, 126 Priority sector lending role of financial institutions through, 208–210 Priority theory of sustainable finance, 147–148 PRISMA 2020 Flow Diagram, 133 Private Banks, 8, 18 Private companies, 91 Private giants, 89 Private Sector Banks, 3 Production-linked Incentive Scheme (PLI Scheme), 207 Profitability, 5 of Indian banks, 7 Programmable integrated circuits (PLCs), 22 Public policies, 84 Public Sector Banks, 3, 8, 18 Python application, 112, 114 Qualitative research techniques, 85 Quality assessment, 134 Quasi-legal enterprises, 56 Real-time resource monitoring techniques, 85 Refugee Olympic, 237 Regional Rural Banks (RRB), 2–3 Relative frequency, 183 Renewable energy, 22, 201, 207 investment target for renewable energy generation, 201–202 Research methodology, 85 Reserve Bank of India (RBI), 2, 6, 99, 207 funds transfer mechanism as per RBI guidelines, 105 Reserve Bank of India Act (1934), 2, 4 Resource allocation, 76 Retail business analytics, 219 Retail customers, 218–219 Retail digital promotion, 220–221 Retail industry, 221 Retail scenario in India, 217–218 Retail stores, 216 Retailers, 216–217, 229 Retailing, 220 data analysis, 224–229 data collection, 223–224 development of conceptual model, 221–223 drivers of digitisation and AI in retail, 218–219 implications of study, 229–230 limitation, scope for further research, 230 literature review and hypothesis development, 217 research methodology, 223–223 research objectives, 217 retail digital promotion, 220–221 retail digitisation using AI, 219–220 retail scenario in India, 217–218 Reward system, 247 Rio Olympic (2016), 236 Scalability, 252 Schedule Banks, 4 Scheduled banks, 2 Search strategy, 133 Security awareness training for employees in SMEs, frequency of, 37–38 Security controls in SME, current state of, 34 Security objectives, 27, 29 Selection criterion, 133–134 Sentiment analysis, 238 method, 114 perspective, 111–112 Sentiments, 236 Sin stocks, 80 Small and Medium Enterprises (SME), 22, 31 age of, 32 analysis of research interview results, 41 analysis of research survey results, 32 biggest problems faced by SMEs implementing or deciding/planning to implement cybersecurity controls, 38–39 core cybersecurity concepts, 26–31 current state of administrative security controls in, 35–37 current state of implemented standards or framework in, 32–33 current state of physical security controls in, 34–35 current state of security controls in, 34 current state of technical security controls in, 35 DLCI framework, 41–48 DLCI Level, 45–46 DMCAS Level, 44 experience of cyberattacks faced by, 39–40 frequency of security awareness training for employees in, 37–38 literature review, 24–26 methodology, 31–32 minimum overall cybersecurity controls implementation level, calculate, 44–45 responsible AI for mapping cybersecurity controls for, 46–48 WCCI for, 44 Small and medium-sized businesses (SMBs), 23, 101 Small business owners, 109 Small finance banks, 2–4 Smart Analytics, 252, 254–255 ability of AI and SA to improve PM systems, 257 AI in HR management, 259 application of AI and SA in business processes, 255 automating PM Systems, 259–261 benefits of, 255 classification models to predict employee performance, 257–259 limitations of AI and SA in PM systems, 261–262 in PM systems, 257 SA in business processes, 256–257 Smart cities, investment target to set up, 203–204 Social accounting, 148 Social media, 219, 235 Social reporting, 146 Socially responsible investments (SRI), 74–76, 79–81 action plan for resolving financial crimes using SRI–ESG Model, 81 current market trend of SRI in India, 74–75 effects of financial crimes, 79 ESG and SRI, 79–81 findings of study, 77 heterogeneity, 76 in India, 75 investors, limitations of study, 77 research 77 research methodology, 77 review of socially responsible 75–76 76 terrorism financing devastating part of financial 78–79 impact of unethical investments on financial crimes, 79 unethical investors, 77–78 41 energy generation, 201 234 234 239 239 149 in PM Systems, 247–248 107 Bank of India 2 Data Analysis, 224 theory 235 modelling 224 model of data analysis, 226–229 178 chain management, 140 income model, implication of model, implications for or for sustainability, 151–152 profit, 206 149 Sustainable development, 206 Sustainable development Sustainable economic development, 140–141 Sustainable economic goals, role of financial institutions in 206–207 Sustainable 147 Sustainable growth in India, 206 security 26 18 249 (Private 89 98 controls, 35 security controls in SME, current state of, 35 132 and AI, 221 companies, 98 Technology and and model Technology governance data sciences in economic and social issues, 86–87 India’s stance on data-driven policy, 87–89 research and methodology, findings and 22 frequency 179 investigating TF-IDF, 182–184 financing on Indian economy, impacts of, 127–128 59 financing, 79 devastating part of financial 78–79 nexus of, 125 threat agents, 24 analysis, 178 data methods, 178 agents, 24 Tokyo Olympic (2020), 234 data analysis and findings, literature review, research methodology, 236 Tokyo Olympic 234 179 relationship between money laundering and economic and financial performance in, 184–185 profit, action 236 PM systems, 252 149 253 234 content analysis, 236 data, 236 sentiments, 235 laundering system, 59 investments on financial crimes, impact of, 79 investors, 77–78 payments 6 Union Bank, 7, 10 56 National Security 28 224 analysis, 60 60, 135 23 87 40 of 173 Cybersecurity Implementation 44 22 23 Yes Bank, 7, 18 25 COVID 19 and Financial Performance of Banks in and of Least Cybersecurity for Small and Medium Enterprises for Global Digitalised Economy Money of from to Socially for Financial Technology and of Governance and Policy-making for the the Sentiment Analysis of Cashkumar Peer-to-Peer Lending on Google of Money Laundering and Financing on the Indian Economy the on Implementation of in Earnings Management for Income of Sustainable COVID-19 Global Debt to the Analysis of Money Laundering Research the Central Bank Digital for Payments and Green Banking to Sustainable Economic Digitisation and Artificial Intelligence in Sector on Sentiment Analysis in 2020 Smart and AI for Modern Performance Management

Objective: To make an extensive analysis of sentiment within the discourse surrounding COVID-19 vaccines on Twitter, employing Natural Language Processing (NLP) methodologies. Method: The research methodology encompasses data collection via the Twitter API, followed by sentiment analysis facilitated by the TextBlob library. Pre-processing stages are integrated to cleanse and standardize the Twitter data. Subsequently, sentiment analysis categorizes tweets into positive, negative, and neutral sentiments based on polarity scores. Findings: The findings, grounded in a dataset spanning from March 1, 2022, to April 30, 2022, comprising 61,934 tweets, unveil that 45.0% of tweets conveyed positive sentiment, 17.3% exhibited negativity, and 37.7% maintained neutrality. Moreover, an exploration of tweet subjectivity revealed that 70.1% of the content expressed subjectivity, while 29.9% conveyed objectivity. The research is augmented with visual representations, including word clouds and subjectivity-polarity graphs, that offer a more intuitive understanding of sentiment trends. Novelty: This study contributes to the expanding landscape of sentiment analysis and its application within the context of public health crises, empowering stakeholders with valuable knowledge to enhance vaccine acceptance and effectiveness. The tool used “Tweet Downloader” in data collection makes this study different from other reviewed studies. Keywords: COVID-19 vaccine, Twitter sentiment analysis, Public perception, Natural Language Processing (NLP), Social media data

Online networking has gotten more consideration these days. Public and private sentiment about a wide assortment of subjects are communicated and spread consistently by means of various internet based life. Twitter is one of the internet based life plateform that is picking up notoriety. Twitter offers associations a quick and compelling approach to break down clients' viewpoints toward the basic to achievement in the commercial center. Building up a program for sentiment analysis is a way to deal with is utilized to computationally quantify client’s recognitions. Twitter sentiment analysis is the method for recognizing feelings and polarity in tweets. The primary computational strides right now deciding the extremity or notion of the tweet and afterward ordering them into the positive tweet or negative tweet or neutral tweet. The essential issue with Twitter sentiment analysis is the distinguishing proof of the most appropriate sentiment classifier that can accurately group the tweets. For the most part, base classification methods like Naive Bayes classifier, Random Forest classifier, SVMs and so on are being utilized. The objective of this paper is to anticipate feelings for the given Twitter post utilizing Python. Sentiment analysis can predict a wide range of feelings joined to the content, however right now 3 significant were considered: positive, negative and neutral. The training dataset is (a little more than 5900 models) and the information inside it is exceptionally skewed, which incredibly affected on the trouble of building great classifier. Subsequent to making a great deal of custom highlights, using both bag-of-words and word2vec portrayals and applying distinctive classification techniques, we accomplish great precision and accuracy for 3 emotions.

The blast of social media has driven to a tremendous sum of user-generated information, especially on stages like Twitter where individuals express their sees and feelings openly. Opinion mining develops as a capable instrument to extricate profitable bits of knowledge from this unstructured information. Twitter serves as a rich resource for comprehending user sentiments and public viewpoints across diverse domains such as politics, current events, consumer behaviors, and brand perception. With the exponential growth in tweet volume, manual analysis of this vast dataset proves impractical. This paper digs into opinion investigation strategies particularly custom fitted for Twitter. Therefore, we are going to analyze different opinions or emotions of users and for this we will use a sentiment analysis approach. Sentiment analysis is an approach to analyzing data and capturing the emotions it embodies. Twitter Sentiment Analysis is the application of sentiment analysis to data from Twitter (Tweets) to extract the sentiments sent by users. The paper moreover examines common assessment measurements utilized to survey the adequacy of these procedures. By giving a comparative investigation, this overview points to prepare analysts and specialists with a comprehensive understanding of estimation investigation on Tweets. This information can be saddled for different applications, such as gaging open conclusion on current occasions, observing brand notoriety, or illuminating promoting techniques. Keywords Dataset, Sentiment analysis, Random Forest, Challenges and Future, Stopford’s, NLP etc.

This paper describes SiTAKA, our system that has been used in task 4A, English and Arabic languages, Sentiment Analysis in Twitter of SemEval2017. The system proposes the representation of tweets using a novel set of features, which include a bag of negated words and the information provided by some lexicons. The polarity of tweets is determined by a classifier based on a Support Vector Machine. Our system ranks 2nd among 8 systems in the Arabic language tweets and ranks 8th among 38 systems in the English-language tweets.

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.

The huge resources need effectiveness and efficiency, it can be processed by machine learning. There have been many studies conducted using machine learning method and produced quite good performance in sentiment analysis. Some machine learning methods that are often used in general are Naive bayes (NB), K-nearest neighbor (KNN), Support vector machine (SVM), and Random forest methods. Mostly, KNN did not achieve better performance than other machine learning methods in sentiment analysis. In this study, the Polarity v2.0 from Cornell movie review dataset will be used to test KNN with Information gain features selection in order to achieve good performance. The purpose of this research are to find the optimum K for KNN and compare KNN with other methods. KNN with the help of Information gain feature selection becomes the best performance method with 96.8% accuracy compared to the NB, SVM, and Random forest while the optimum K is 3.

Twitter serves as a dynamic platform for real-time communication, where users share opinions, news, and trends globally. The vast volume of daily tweets provides a rich source for sentiment analysis, enabling organizations to effectively gauge public opinion and consumer sentiment. This data-driven analysis not only supports marketing strategies but also enhances decision-making in areas like politics, public health, and brand management. However, several studies face limitations such as low data quality, contextual challenges, and resource intensive. To address these issues, this study evaluates the performance of three models, Bert, RoBERTa, and DistilBERT- on Twitter sentiment analysis. The models are assessed based on accuracy, precision, recall, and F1-score. Among the models, RoBERTa demonstrates the highest performance for both positive and negative sentiment analysis.

Abstract. This system was developed to determine the accuracy of sentiment analysis on Twitter regarding the COVID-19 issue using the Nazief-Adriani and Porter stemmers with TF-IDF weighting, along with a classification process using K-Nearest Neighbor (KNN) that resulted in a comparison of 48.24% for Nazief-Adriani and 48.24% for Porter. Purpose: This research aims to determine the accuracy of the Nazief-Adriani and Porter stemmer algorithms in performing text preprocessing using a dataset from Indonesian-language Twitter. This research involves word weighting using TF-IDF and classification using the K-Nearest Neighbor (KNN) algorithm. Methods/Study design/approach: The experimentation was conducted by applying the Nazief-Adriani and Porter stemmer algorithm methods, utilizing data sourced from Twitter related to COVID-19. Subsequently, the data underwent text preprocessing, stemming, TF-IDF weighting, accuracy testing of training and testing data using K-Nearest Neighbor (KNN) algorithm, and the accuracy of both stemmers was calculated employing a confusion matrix table. Result/Findings: This study obtained reasonably accurate results in testing the Nazief-Adriani stemmer with an accuracy of 50.98%, applied to sentiment analysis of COVID-19-related Twitter data using the Indonesian language. As for the accuracy of the Porter stemmer, it achieved an accuracy rate of 48.24%. Novelty/Originality/Value: Feature selection is crucial in stemmer accuracy testing. Therefore, in this study, feature selection is carried out using the Nazief-Adriani and Porter stemmers for testing purposes, and the accuracy data classification is conducted using the K-Nearest Neighbor (KNN) algorithm

Blogs, internet forums, social networks, and micro-blogging sites are some of the growing number of places where users can voice their opinions. Opinions on any given product, issue, service, or idea are contained in data, making them a valuable resource in their own right. Popular social networking services like Twitter, Facebook, and Google+ allows expressing views on a variety of topics, participating in discussions, or sending messages to a global user. Twitter sentiment analysis has received a lot of attention recently.Sentiment analysis is finding how a person feels about a topic from their written response about it and it can be separated into positive and negative through its use. Doing so enables to classify the tweets made by a user in to appropriate classification category based on which some decisions can be made. The literature proposed approaches to develop the classifiers on the Twitter datasets. Operations, including tokenization, stop-word removal, and stemming will be performed. NLP converts the text to a machine-readable representation. Artificial Intelligence (AI) combines NLP data to evaluate if a situation is positive or negative. The document’s subjectivity can be identified using ML and NLP techniques to categorize them in to positive, neutral, or negative. Performing sentiment analysis in Twitter data can be tedious due to limited size, unstructured nature, misspellings, slang, and abbreviations. For this task, a Tweet Analyzing Model for Cluster Set Optimization with Unique Identifier Tagging (TAM-CSO-UIT) was built using prospects to determine positive or negative sentiment in tweets obtained from Twitter. This approach assigns a +ve/-ve value to each entry in the Tweet database based on probability assignment using n-gram model. To perform this effectively the tweet dataset is considered as a sliding window of length L. The proposed model accurately analyses and classifies the tweets.

In this paper we report our works for SemEval-2014 Sentiment Analysis in Twitter evaluation challenge. This is the first time we attempt for this task, and our submissions are based on supervised machine learning algorithm. We use Support Vector Machine for both the tasks, viz. contextual polarity disambiguation and message polarity classification. We identify and implement a small set of features for each the tasks, and did not make use of any external resources and/or tools. The systems are tuned on the development sets and finally blind evaluation is performed on the respective test set, which consists of the datasets of five different domains. Our submission for the first task shows the F-score values of 76.3%, 77.04%, 70.91%, 72.25% and 66.32% for LiveJournal2014, SMS2013, Twitter2013, Twitter2014 and Twitter2014Sarcasm datasets, respectively. The system developed for the second task yields the F-score values of 54.68%, 40.56%, 50.32%, 48.22% and 36.73%, respectively for the five different test datasets.

Sentiment analysis is an important task in natural language processing. Twitter sentiment analysis (SA) is the most frequently researched discipline today. Only a few researchers have concentrated on multilingual twitter sentiment analysis, while the majority of scholars have worked on English twitter sentiment analysis. Recently, there seems to be a large increase in the quantity of data sets transmitted via social media in a variety of languages. This work examines the semantic nature of a text in order to classify positive and negative tweets using Hindi and Kannada language models, respectively. Machine learning models such as Naïve Bayes Classifier, KNeighbors’ Classifier, Decision Tree Classifier and Random Forest Classifier are used to tackle the classification task.

Introducing two Random Forest based methods for cloud detection in remote sensing images