Inverted LSB image steganography using adaptive pattern to improve imperceptibility

In recent years, an increasing number of researchers have focused on the aspect-level sentiment analysis in the field of natural language processing. A coarse-grained sentiment analysis at the document level and a sentiment analysis at the sentence level can only judge an entire text comprehensively, whereas a fine-grained sentiment analysis distinguishes each concrete aspect of the text and makes separate judgments on the sentiment polarity. The word vector representation obtained by a recurrent neural network lacks a description of the distance relationship between the context words and aspect, and traditional models rarely consider the influence of the association between contextual sentences. In this paper, we propose an aspect-level sentiment analysis model with aspect-specific contextual location information. By designing two asymmetrical contextual position weight functions respectively, the model adjusts the weight of contextual words according to the positions of the aspect words in the sentences, and alleviates the interference of the difference in the number of words on both sides of the aspect words on the judgment of sentimental polarity. By utilizing single-sentence-level and multiple-sentence-level bidirectional GRU layers, model will extract the influence of the contextual association of each sentence in the document on the aspect sentiment polarity of individual sentences. In addition, we analyze the distribution properties of hard samples and design a novel loss function for the class imbalance problem in the field of sentiment analysis. For dataset 15Rest, the accuracy of our model is 4.27% higher than that of ASGCN, whereas the f1-score, which is more indicative of the classification performance on an imbalanced dataset, can be seen to be improved by 4.31% in comparison to the ASGCN. 

Aspect-level sentiment analysis with aspect-specific context position information

Aspect-level sentiment analysis aims at identifying the sentiment polarity of specific aspect words in a given sentence. Existing studies mostly use recurrent neural network (RNN) -based models. However, truncated backpropagation, gradient vanishing, and exploration problems often occur during the training process. To address these issues, this paper proposed a novel network with multiple attention mechanisms for aspect-level sentiment analysis. First, we apply the bidirectional encoder representations from transformers (BERT) model to construct word embedding vectors. Second, multiple attention mechanisms, including intra- and inter-level attention mechanisms, are used to generate hidden state representations of a sentence. In the intra-level attention mechanism, multi-head self-attention and point-wise feed-forward structures are designed. In the inter-level attention mechanism, global attention is used to capture the interactive information between context and aspect words. Furthermore, a feature focus attention mechanism is proposed to enhance sentiment identification. Finally, several classic aspect-level sentiment analysis datasets are used to evaluate the performance of our model. Experiments demonstrate that the proposed model can achieve state-of-the-art results compared to baseline models.

A novel network with multiple attention mechanisms for aspect-level sentiment analysis

Graph convolutional network with multiple weight mechanisms for aspect-based sentiment analysis

High-capacity adaptive steganography based on LSB and Hamming code

The aim of aspect-level sentiment analysis is to identify the sentiment polarity of a given target term in sentences. Existing neural network models provide a useful account of how to judge the polarity. However, context relative position information for the target terms is adversely ignored under the limitation of training datasets. Considering position features between words into the models can improve the accuracy of sentiment classification. Hence, this study proposes an improved classification model by combining multilevel interactive bidirectional Gated Recurrent Unit (GRU), attention mechanisms, and position features (MI-biGRU). Firstly, the position features of words in a sentence are initialized to enrich word embedding. Secondly, the approach extracts the features of target terms and context by using a well-constructed multilevel interactive bidirectional neural network. Thirdly, an attention mechanism is introduced so that the model can pay greater attention to those words that are important for sentiment analysis. Finally, four classic sentiment classification datasets are used to deal with aspect-level tasks. Experimental results indicate that there is a correlation between the multilevel interactive attention network and the position features. MI-biGRU can obviously improve the performance of classification.

/pdf/aspect-level-sentiment-analysis-based-on-position-features-2cctjz7igk.pdf

Aspect-Level Sentiment Analysis Based on Position Features Using Multilevel Interactive Bidirectional GRU and Attention Mechanism

In Sina-microblog comments, abundant emojis, as an important piece of information for the sentiment analysis, are used to vividly express users's opinions and feelings. To classify timely and effectively the sentiment hidden in the vast pool of the microblog comments, this paper proposes an emojis-enhanced sentiment analysis model. The model first extracts emojis from review sentences and constructs emoji sequences as an enhanced information, and then uses BiLSTMs to learn text-based representation. Furthermore, this model adopts a new attention mechanism to incorporate contextual information of sentences into emojis to learn the emoji-based auxiliary representation. Finally, the final representation is obtained by combining text representation and emoji representation through the full connection layer. Extensive experiments show the effectiveness of the proposed method on sentiment classification for Chinese microblog comments.

A Deep Learning Model Enhanced with Emojis for Sina-Microblog Sentiment Analysis

Image steganography is a technique for hiding secret data in cover image. In recent years, chaotic systems have become increasingly important in steganography. This paper proposes an embedding technique based on cyclic chaos, which effectively embeds secret messages into color images. The cyclic chaos is divided into two parts: the chaotic function of generating seeds and the pseudo random number generator (PRNG). A pixel is found through the chaotic cycle system, and a three-bit secret message is embedded into the R, G, and B channels of the pixel through a specific embedding algorithm. Compared with other color image embedding methods, the proposed algorithm has higher visual quality and improved security.

Zhen Wang

Papers

High-capacity adaptive steganography based on LSB and Hamming code

A novel network with multiple attention mechanisms for aspect-level sentiment analysis

Aspect-Level Sentiment Analysis Based on Position Features Using Multilevel Interactive Bidirectional GRU and Attention Mechanism

A Deep Learning Model Enhanced with Emojis for Sina-Microblog Sentiment Analysis

LSB Color Image Embedding Steganography Based on Cyclic Chaos