![keras one-hot text encoding keras one-hot text encoding](https://mlln.cn/2018/07/16/keras教程-02-tensorflow和keras安装/images/keras_tf_twitter_poll.jpg)
The model with the best performance showed 0.99 F1-Score and 0.95 Accuracy however, after the programme testing, a few weaknesses were found. The neural network training was implemented with the Tesla T4 graphics processing unit on the Google Colab platform. The experiments centered around the development, evaluation and comparative analyses of two models - based on Bag-of-Words and Word Embeddings, respectively. In the latter case publications are not related to drug addiction issues. The second type of communities focuses on the discussion of private issues - the users share their life stories and ask for help or advice. The first type includes communities which actively discuss problems of addiction to psychotropic and psychoactive substance. The dataset comprises texts of publications and comments posted in two types of open communities. The classifier is based on the dataset from Russian-speaking online VK (VKontakte) communities. It may also provide insights on the features of addicts’ online discourse. This system may find application in healthcare as a tool for automatic identification of addicts’ communities.
![keras one-hot text encoding keras one-hot text encoding](https://i.ytimg.com/vi/UpHO3gLYN8c/maxresdefault.jpg)
The purpose of the classifier is to recognise messages published in virtual communities of drug-addicted people. The paper describes building a binary classifier with Convolutional Neural Network (CNN) using two different types of word vector representations, Bag-of-Words and Word Embeddings.