Ontology-Based Approach to Social Data Sentiment Analysis: Detection of Adolescent Depression Signals

Suicide Risk Assessment Using Machine Learning and Social Networks: a Scoping Review

“…From the full-text review, 16 articles were then selected for inclusion [26,[42][43][44][45][46][47][48][49][50][51][52][53][54][55][56]. The flow diagram representing the search process is shown in Fig.…”

“…Jung et al 2018 [50] have implemented an ontology and terminology method to provide a semantic foundation for analyzing social media data on adolescent depression. They evaluated the ontology obtaining the best values of precision (76.1%) and accuracy (75%) using DT algorithms.…”

“…Feature extraction and feature selection were identified as main objectives in four different studies (4/16, 25%) [48,50,53,56]. The remaining categories (Entity Recognition, Theme Identification and Emotion Recognition) were identified only in a study (1/16, 6.25%) [47,49,55].…”

“…Three of them used sample sizes with more than 800 posts. Five studies reported dataset sizes between 1000 and 5000 posts (33.33%) [45,47,50,52,53]. Finally, six studies used large dataset, including more than 10,000 posts (40%).…”

The Identification Of Cortical Pyramidal Neurons Using A Rpp Based Algorithm

“…From the main process of cortical pyramidal neuron characterization we can see that the feature mining and processing as well as classifier selection are the main factors that affect the characterization performance. The Factor Algorithm (FA) [1], Linear Differential Algorithm (LDA) [2] and Regularization Preserving Estimates (RPP) [3] algorithm have been proved to be able to greatly improve the characterization rate. It is found that the cortical pyramidal neuron global feature mining can represent the cortical pyramidal neuron overall contour and any other global data, but it is sensitive to changes of illumination and posture.…”