Biblio

Text Mining is widely used in many areas transforming unstructured text data from all sources such as patients' record, social media network, insurance data, and news, among others into an invaluable source of information. The Bag Of Words (BoW) representation is a means of extracting features from text data for use in modeling. In text classification, a word in a document is assigned a weight according to its frequency and frequency between different documents; therefore, words together with their weights form the BoW. One way to solve the issue of voluminous data is to use the feature hashing method or hashing trick. However, collision is inevitable and might change the result of the whole process of feature generation and selection. Using the vector data structure, the lookup performance is improved while resolving collision and the memory usage is also efficient.

The traditional text classification methods usually follow this process: first, a sentence can be considered as a bag of words (BOW), then transformed into sentence feature vector which can be classified by some methods, such as maximum entropy (ME), Naive Bayes (NB), support vector machines (SVM), and so on. However, when these methods are applied to text classification, we usually can not obtain an ideal result. The most important reason is that the semantic relations between words is very important for text categorization, however, the traditional method can not capture it. Sentiment classification, as a special case of text classification, is binary classification (positive or negative). Inspired by the sentiment analysis, we use a novel deep learning-based recurrent neural networks (RNNs)model for automatic security audit of short messages from prisons, which can classify short messages(secure and non-insecure). In this paper, the feature of short messages is extracted by word2vec which captures word order information, and each sentence is mapped to a feature vector. In particular, words with similar meaning are mapped to a similar position in the vector space, and then classified by RNNs. RNNs are now widely used and the network structure of RNNs determines that it can easily process the sequence data. We preprocess short messages, extract typical features from existing security and non-security short messages via word2vec, and classify short messages through RNNs which accept a fixed-sized vector as input and produce a fixed-sized vector as output. The experimental results show that the RNNs model achieves an average 92.7% accuracy which is higher than SVM.