Algorithm for measurement and analysis of authority and influence of users in social and professional networks

The measurement and analysis of the authority and influence exercised by a person in an organization or social network, be it formal or informal, has been the subject of numerous researches in several fields of science. At present, this phenomenon has taken on greater connotation due to its irruption in the digital space and the importance of having this knowledge for decision-making in spheres such as politics, education and the dissemination of information. In this research, an algorithm was developed for the measurement and analysis of the authority and influence of users in social and professional networks. The study had a mixed approach, with correlational scope and experimental design. A random sample n = 30 specialists was used, which was carried out between May 2019 and October 2020. It was based on the premise that, in order to carry out an adequate measurement and analysis of authority and influence, the structure of the graph must be considered that represents the social network and the interactions that occur between users. As a result, the Total Authority algorithm is developed, a computer tool for the generation of the graph and a case study, which evaluates its relevance, operation and applicability, which shows satisfactory results in its comparison with the HITS algorithm and a sociogram.

Using Eco-Geographical Zoning Data and Crowdsourcing to Improve the Detection of Spurious Land Cover Changes

To address problems in remote sensing image change detection, this study proposes a method for identifying spurious changes based on an eco-geographical zoning knowledge base and crowdsourced data mining. After preliminary change detection using the super pixel cosegmentation method, eco-geographical zoning is introduced, and the rules of spurious change are collected based on the knowledge of expert interpreters, and from statistics on existing land cover products according to each eco-geographical zone. Uncertain changed patches with a high possibility of spurious change according to the eco-geographical zoning rule were published in the form of a map service on an online platform, and then crowd tagging information on spurious changed patches was collected. The Hyperlink-Induced Topic Search (HITS) algorithm was used to calculate the spurious change degree of changed patches. We selected the northern part of Laos as the experimental area and the Chinese GF-1 Wide Field View (WFV) images for change detection to verify the effectiveness of the method. The results show that the accuracy of change detection improves by 23% after removing the spurious changes. Spurious changes caused by clouds, river water turbidity, spectral differences in cultivated land before and after harvest, and changes in shrubs, grassland, and forest density, can be removed using an eco-geographical zoning knowledge base and crowdsourced data mining methods.

Identification of Fictitious Messages in Social Network using E-Hits and Newsapi

Social network has become a primary resource for users to send and receive the foremost up-to-date data and trend the present events. Currently, most of the social network contains the fictional content that was created by the influential spreaders wherever the message originality and therefore the spreader identity cannot be found which affects the end users. The proposed models to discover fictitious messages are verifying the contextual integrity with the trained classifier using large datasets. But the problem lies in updating of datasets with the recent or trending events from trusted sources in a regular interval. In the existing model, Hypertext-Induced Topic Search (HITS) method has been used for rating posts based on hub score and authority score. The hub score is calculated based on how many posts are posted or liked or tagged by the user and authority score is calculated based on how many users liked or tagged a post. If the user who ranks high in hub score tries to trend the low ranked post in authority score, the user will be marked as spreader. But the problem lies in the identification and verification of the posts that ranks in authority score. In our proposed system, we have enhanced the HITS algorithm by adding a third mechanism called top score which assigns weightage for every post based on the time they have posted. The time and content of the post has been verified by theintegrated new model NewsAPI. Based on the three scores, the posts are filtered and matched with the news collected from NewsAPI. The news or posts that have not been matched either with the context or with the time will be marked as fictitious.

An Ontology-based Ranking Model in Search Engines

As the tsunami of data has emerged, search engines have become the most powerful tool for obtaining scattered information on the internet. The traditional search engines return the organized results by using ranking algorithm such as term frequency, link analysis (PageRank algorithm and HITS algorithm) etc. However, these algorithms must combine the keyword frequency to determine the relevance between user’s query and the data in the computer system or internet. Moreover, we expect the search engines could understand users’ searching by content meanings rather than literal strings. Semantic Web is an intelligent network and it could understand human’s language more semantically and make the communication easier between human and computers. But, the current technology for the semantic search is hard to apply. Because some meta data should be annotated to each web pages, then the search engine will have the ability to understand the users intend. However, annotate every web page is very time-consuming and leads to inefficiency. So, this study designed an ontology-based approach to improve the current traditional keyword-based search and emulate the effects of semantic search. And let the search engine can understand users more semantically when it gets the knowledge.