Scalability and Performance Evaluation of Machine Learning Techniques in High-Volume Social Media Data Analysis

2022 10th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO), Journal Year: 2024, Volume and Issue: unknown

Published: March 14, 2024

In the modern era of digital communication, social media platforms are data factories and hence provide a new set opportunities as well challenges before analysts. The objective this paper is to evaluate scalability performance various ML algorithms for analysis in practice with high-volume datasets. design that scalable achieve high accuracy when used big literature survey, observed gaps present research advancements toward techniques intent. To make sure diversity size, we collected source from different networks. approach did involve assessing number methods widely known like natural language processing (NLP), sentiment (SA) predictive analytics on factors such time process resource utilization while also considering metrics precision recall rate f1 score. results demonstrate significant differences investigated approaches their quality, some being more efficient or accurate at large scale. This adds value existing works area, by performing detailed comparative study large-scale vs tradeoffs. findings informative, community, selection suitable will be applicable analytics; an important factor dominated data. future research, advanced hybrids should taken into account enhance analysis.

Language: Английский

---

Comparative Analysis of Machine Learning Techniques for Detecting Sentiments in Social Media

Published: March 15, 2024

This paper provides an extensive discussion of the machine learning algorithms applied to sentiment analysis on social media, involving use Naive Bayes, Support Vector Machines (SVM), and Deep models evaluation comparison. The growth network content at rates exponential, computerized assessment interpretation valuer client have become extremely important serve areas market researches from opinion monitoring. We conducted a systematic study viability various methodologies that aim deal with complicated characteristics as well peculiar nature Language Processing Natural (LPN), which are most-likely caused by enormous amount data media platforms. According our results, Learning based incorporate more complex neural structure thus, CNNs RNNs likely outperform other explanations. critical point their success lies in power capture semantic contextual language. Nevertheless, exploration also outlines computational needs methods, imply some requirements for contemporary applications. cover issues processing speed trade-offs terms classification accuracy versus efficiency, thus out implementation problems scaled adoption brings.

Language: Английский

---

Enhancing Accuracy in Social Media Sentiment Analysis through Comparative Studies using Machine Learning Techniques

Published: April 18, 2024

Language: Английский

---

Integration of Machine Learning Algorithms for Predictive Maintenance in IoT-Enabled Smart Safety Helmets

Published: May 24, 2024

Language: Английский

---

Impact of Machine Learning on Applying the Best Worst Method for Social Sustainability in Manufacturing Supply Chains

Published: Aug. 8, 2024

Language: Английский

---

Advanced Machine Learning Approaches to Evaluate User Feedback on Virtual Assistants for System Optimization

Published: July 10, 2024

Language: Английский

---

Machine Learning Applications in Azure for Enhanced E-commerce Customer Sentiment Analysis

Published: Aug. 8, 2024

Language: Английский

---

Accelerating Sustainability through Leveraging Machine Learning to Analyze CSR Spending in the Indian Automobile Industry

Published: Aug. 8, 2024

Language: Английский

---

Integrating AI and Machine Learning Into Supply Chain and Marketing

Advances in marketing, customer relationship management, and e-services book series, Journal Year: 2024, Volume and Issue: unknown, P. 189 - 218

Published: Oct. 18, 2024

Artificial Intelligence and its subdivision, Machine Learning pose the question of effective incorporation intelligent technology into supply chain marketing functions. Controlling these constraints achieving efficiency, accuracy, scalability in handling rise data volumes require a deeper understanding AI ML's bi-end applications essential areas displays how both can be implemented explicitly decreasing processes, assigning resources efficiently obtaining comprehensive analytical results. The learning process is supported by real examples ML application demand forecasting, inventory management, logistics systems, personalized marketing, analysis customers' behavior. Thus, outlining technologies integrated strategically within business, this chapter seeks to help organisations innovate sustain competitive advantage ever-evolving sphere marketing.

Language: Английский

---

Revolutionizing Supply Chains With AI and Machine Learning

Advances in marketing, customer relationship management, and e-services book series, Journal Year: 2024, Volume and Issue: unknown, P. 283 - 312

Published: Oct. 18, 2024

Supply chain management with AI and its enhancement, the ML, is witnessing vast change opens up a brand-new vista of chances for improved effectiveness, precision, creativity. The perspectives implementing actual cases companies use ML are discussed in this chapter as means increasing efficiency functioning supply chains at different stages including demand forecasting, inventory management, logistics, supply. In presented case studies descriptions implementations technologies, we underscore pragmatic outcomes competitive edge(es). addition, also some catalyzes that may hinder adoption including; Limited poor quality data, high cost implementation need to employ qualified personnel area ML. We touch on how above barriers can be addressed such technologies implemented chain.

Language: Английский

---