NSLPCD: Topic based tweets clustering using Node significance based label propagation community detection algorithm

Abstract

Social networks like Twitter, Facebook have recently become the most widely used communication platforms for people to propagate information rapidly. Fast diffusion of information creates accuracy and scalability issues towards topic detection. Most of the existing approaches can detect the most popular topics on a large scale. However, these approaches are not effective for faster detection. This article proposes a novel topic detection approach – Node Significance based Label Propagation Community Detection (NSLPCD) algorithm, which detects the topic faster without compromising accuracy. The proposed algorithm analyzes the frequency distribution of keywords in the collection of tweets and finds two types of keywords: topic-identifying and topic-describing keywords, which play an important role in topic detection. Based on these defined keywords, the keyword co-occurrence graph is built, and subsequently, the NSLPCD algorithm is applied to get topic clusters in the form of communities. The experimental results using the real data of Twitter, show that the proposed method is effective in quality as well as run-time performance as compared to other existing methods.

A Review on Human–AI Interaction in Machine Learning and Insights for Medical Applications

“…Providing data labels for the whole data set by only humans is a hard, time consuming and tiresome task [ 47 ]. So different algorithms and ML methods have been presented to improve data tagging process in which the advantages of humans and their cognitions cannot be denied.…”

“…For example, Feder et al [ 25 ] employed humans to relabel a very small fraction of training data which was wrongly classified by classifiers in their proposed active learning approach to detect demographic traits in clinical notes. In [ 47 ], a human-in-the-loop active learning method was presented based on brain-computer interface and deep learning to tag target visual data during the training process. In the proposed method, users were connected to the electroencephalograms electrodes and images include target images and non-target images were shown to them as a rapid serial visual presentation.…”

“…To exemplify, in Rocettin et al [ 4 ], human experts interacted with ML once by defining some semantics to select the high-quality data set instances in order to improve the prediction power of the neural network. In Netzer and Geva [ 47 ], human experts collaborated with ML process once for data labelling to tag target visual objects in images. In Yuksel et al [ 34 ], human refined the ML results once at the end of producing video description for blinded people.…”

Recent Research Topic Detection and Analysis using IFCM

“…The exponential growth of research publications enlarge with new trends of computational geometry. Hence, new topic detection among computational geometry is very challenging research [4].…”

Type2 IFC with SOA for Topic Detection and Document Clustering Analysis

“…A large number of online scientific publications are written on the World Wide Web or on the Internet every day in the digital era [1]. There is generally increased interest in identifying topics in published scientific papers, including defining boundaries in the scientific field and identifying innovative capabilities, [2] which in turn sets out to be the central part of the process of producing scientific knowledge. Resource-rich research demands knowledge of earlier research and technology [3].…”