학술논문

Perceptions Unveiled: Analyzing Public Sentiment on IoT and AI Integration in Revolutionizing Social Interactions
Document Type
Conference
Source
2023 7th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC) I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC), 2023 7th International Conference on. :65-70 Oct, 2023
Subject
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Robotics and Control Systems
Symbiosis
Sentiment analysis
Ethics
Technological innovation
Logistic regression
Social networking (online)
Blogs
Internet of Things (IoT)
Artificial Intelligence(AI)
Natural Language Processing (NLP)
TFIDF Vectorization
Linear Support Vector Classification (LinearSVC)
Language
ISSN
2768-0673
Abstract
The IoT and AI are transforming social connections and communication. The article investigates how this symbiotic relationship impacts Twitter sentiment. Using the Twitter Sentiment Dataset," this study analyzes how IoT and AI are changing linked experiences. Analyzing Twitter sentiment on this historic merger shows positive and negative sentiments. Social media allows people to express their thoughts and feelings. This evolving digital environment reflects society and reveals technology adoption sentiment. The merging of IoT with AI is a key technological achievement. Tweets provide a real-time snapshot of worldwide dialogues and reactions to understand public opinion on integration. This study examines the complicated sentiment landscape using the "Twitter Sentiment Dataset," which captures IoT and AI sentiments. Social media sentiment analysis has been used to study public reactions to technological advances. Several studies show that sentiment analysis can predict technological adoption, examine attitudes and concerns, uncover issues, influence legislation, and address ethical issues. Research also emphasizes sentiment polarization's enthusiasm-realism balance and how sentiment predicts technical impact. The research used the "Twitter Sentiment Dataset," with over 1.6 million tweets. Lowercase, punctuation, and stopwords were removed from the dataset. After that, NLP algorithms like sentiment analysis examined the text. The training and test sets were split, and TF- IDF vectorization retrieved features. This research tested sentiment analysis machine learning models (Bernoulli Naive Bayes, Linear Support Vector Classification, and Logistic Regression). Later, the best model was stored. The main measure of sentiment analysis model accuracy was accuracy. Logistic regression outperformed with 83% accuracy. The models accurately captured IoT and AI integration tweets, including joy and concerns. Sentiment analysis can disclose society's feelings, making IoT-AI integration promising. This study reveals that algorithms and human sentiment drive technology. Technology- emotion interactions affect public opinion, innovation ethics, and policy. The study shows that societal emotion is essential to technical advancement and lays the framework for human-valued IoT and AI.