Globally, depression is perceived as the most recurrent and risky disorder among young people and adults under the age of 60. Depression has a strong influence on the usage of words which can be observed in the form of written texts or stories posted on social media. With the help of Natural Language Processing(NLP) and Machine Learning (ML) techniques, the depressive signs expressed by people can be identified at the earliest stage from their Social Media posts. The proposed work aims to introduce an efficacious depression detection model unifying an exemplary feature extraction scheme and a hybrid Long Short-Term Memory network (LSTM) model. The feature extraction process combines a novel feature selection method called Elite Term Score (ETS) and Word2Vec to extract the syntactic and semantic information respectively. First, the ETS method leverages the document level, class level, and corpus level probabilities for computing the weightage/score of the terms. Then, the ideal and pertinent set of features with a high ETS score is selected, and the Word2vec model is trained to generate the intense feature vector representation for the set of selected terms. Finally, the resultant word vector obtained is called EliteVec, which is fed to the hybrid LSTM model based on Honey Badger optimizer with population reduction technique (PHB) which predicts whether the input textual content is depressive or not. The PHB algorithm is integrated to explore and exploit the optimal hyperparameters for strengthening the performance of the LSTM network. The comprehensive experiments are carried out with two different Twitter depression corpus based on accuracy and Root Mean Square Error (RMSE) metrics. The results demonstrated that the proposed EliteVec+LSTM+PHB model outperforms the state-of-art models with 98.1% accuracy and 0.0559 RMSE.
The proposed work deals with finding related reviews posted on various online Forums. Conventional methods for matching related documents compute the content similarity over the entire review instead of partitioning into segments revealing different intentions. In this work, intention-based similarity clustering is introduced to find the relatedness of two documents. This method forms the document clusters based on the similarity of the segments with similar intentions. The segmentation points are identified using a number of text features which can express when the segmentation should be done. Finally, the document clusters are formed by grouping the segments with similar intentions in same cluster and then the similarities among the segments with the same intention are computed. The proposed model is trained on TripAdvisor and Yelp Open Review datasets to evaluate the performance of the model, and the evaluation results show that the model produces more precise results in mining documents related to the user’s interest.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.