Context-specific discussion of Airbnb usage knowledge graphs for improving private social systems

• Published in: Journal of combinatorial optimization 2023-03, Vol.45 (2), Article 66
• Main Authors: Samsudeen, Salomi, Ali, Mohammed Hasan, Vignesh, C. Chandru, Kamruzzaman, M. M., Prakash, Chander, Thirugnanam, Tamizharasi, Daniel, J. Alfred
• Format: Article
• Language: English
• Subjects: Accuracy; Artificial neural networks; Combinatorics; Context; Convex and Discrete Geometry; Feature extraction; Graphs; Human behavior; Knowledge representation; Machine learning; Mathematical Modeling and Industrial Mathematics; Mathematics; Mathematics and Statistics; Operations Research/Decision Theory; Optical character recognition; Optimization; Public health; Social networks; Theory of Computation
• ISSN: 1382-6905; 1573-2886
• DOI: 10.1007/s10878-023-00994-y

This research concentrates on extracting and context-specific discussion of Airbnb usage knowledge graphs to improve private social systems. The Knowledge-Infused Learning Techniques are applied to the learning and social impact of Airbnb usage user's system. This research Extracting and discusses Airbnb usage using knowledge graphs. This research formulates the two proposed methods for Extracting Airbnb usage knowledge graphs to improve private social systems. This research enables the two potential implications for user expectation Extraction and context-specific discussion about personal social systems. This might be useful to enhance the specific services of personal social systems. This led by using the knowledge graphs concerning the responsibilities and services using response-based Optical Character Recognition. This might be fulfilled with the internal data and explain factor for "Airbnb private systems" based on knowledge graphs and machine learning. However, the Graph convolutional networks work based on the Convolutional Neural Networks for automatically Extracting the essential features without any human supervision based on a context-specific discussion of Airbnb systems. The financial portion of the computational social system application is 45.8%, followed by the public health portion at 56.8%, the environment portion at 69.3%, the politics policy portion at 72%, the social behavior portion at 78%, the human behavior portion at 80%, and the social system portion at 85% better performance in the Airbnb usage knowledge process. The efficiency of this analysis is around 67.9%. The input data second level range is 23–39%, the improved accuracy range is 74.38%, and the increased accuracy range is 46.33%. The enhanced accuracy range is 96.5%, and the third-level input data range is 43–59%. This rough comparison result has an efficiency of 62.51%. The outcomes of several social network comparison experiments are compared to the knowledge-infused learning and classification model, and the estimated result is 73.8% efficient.