Fusion of part-of-speech vectors and attention mechanisms for cross-domain sentiment analysis

The grand challenge of cross-domain sentiment analysis is that classifiers trained in a specific domain are very sensitive to the discrepancy between domains. A sentiment classifier trained in the source domain usually have a poor performance in the target domain. One of the main strategies to solve this problem is the pivot-based strategy, which regards the feature representation as an important component. However, part-of-speech information was not considered to guide the learning of feature representation and feature mapping in previous pivot-based models. Therefore, we present a fused part-of-speech vectors and attention-based model (FAM). In our model, we fuse part-of-speech vectors and feature word embeddings as the representation of features, giving deep semantics to mapping features. And we adopt Multi-Head attention mechanism to train the cross-domain sentiment classifier to obtain the connection between different features. The results of 12 groups comparative experiments on the Amazon dataset demonstrate that our model outperforms all baseline models in this paper.

Download Full-text

Cross-Domain Recommendation Based on Sentiment Analysis and Latent Feature Mapping

Entropy ◽

10.3390/e22040473 ◽

2020 ◽

Vol 22 (4) ◽

pp. 473

Author(s):

Yongpeng Wang ◽

Hong Yu ◽

Guoyin Wang ◽

Yongfang Xie

Keyword(s):

Sentiment Analysis ◽

Latent Dirichlet Allocation ◽

Mapping Function ◽

Linear Mapping ◽

Feature Mapping ◽

Target Domain ◽

User Reviews ◽

Cross Domain ◽

Semantic Orientation ◽

Label Information

Cross-domain recommendation is a promising solution in recommendation systems by using relatively rich information from the source domain to improve the recommendation accuracy of the target domain. Most of the existing methods consider the rating information of users in different domains, the label information of users and items and the review information of users on items. However, they do not effectively use the latent sentiment information to find the accurate mapping of latent features in reviews between domains. User reviews usually include user’s subjective views, which can reflect the user’s preferences and sentiment tendencies to various attributes of the items. Therefore, in order to solve the cold-start problem in the recommendation process, this paper proposes a cross-domain recommendation algorithm (CDR-SAFM) based on sentiment analysis and latent feature mapping by combining the sentiment information implicit in user reviews in different domains. Different from previous sentiment research, this paper divides sentiment into three categories based on three-way decision ideas—namely, positive, negative and neutral—by conducting sentiment analysis on user review information. Furthermore, the Latent Dirichlet Allocation (LDA) is used to model the user’s semantic orientation to generate the latent sentiment review features. Moreover, the Multilayer Perceptron (MLP) is used to obtain the cross domain non-linear mapping function to transfer the user’s sentiment review features. Finally, this paper proves the effectiveness of the proposed CDR-SAFM framework by comparing it with existing recommendation algorithms in a cross-domain scenario on the Amazon dataset.

Download Full-text

Deep Transfer Learning for Biology Cross-Domain Image Classification

Journal of Control Science and Engineering ◽

10.1155/2021/2518837 ◽

2021 ◽

Vol 2021 ◽

pp. 1-19

Author(s):

Chunfeng Guo ◽

Bin Wei ◽

Kun Yu

Keyword(s):

Image Classification ◽

Transfer Learning ◽

Poor Performance ◽

Target Domain ◽

Deep Convolutional Neural Networks ◽

Specific Domain ◽

Source Domain ◽

Cross Domain ◽

Domain Transfer ◽

Domain Transfer Learning

Automatic biology image classification is essential for biodiversity conservation and ecological study. Recently, due to the record-shattering performance, deep convolutional neural networks (DCNNs) have been used more often in biology image classification. However, training DCNNs requires a large amount of labeled data, which may be difficult to collect for some organisms. This study was carried out to exploit cross-domain transfer learning for DCNNs with limited data. According to the literature, previous studies mainly focus on transferring from ImageNet to a specific domain or transferring between two closely related domains. While this study explores deep transfer learning between species from different domains and analyzes the situation when there is a huge difference between the source domain and the target domain. Inspired by the analysis of previous studies, the effect of biology cross-domain image classification in transfer learning is proposed. In this work, the multiple transfer learning scheme is designed to exploit deep transfer learning on several biology image datasets from different domains. There may be a huge difference between the source domain and the target domain, causing poor performance on transfer learning. To address this problem, multistage transfer learning is proposed by introducing an intermediate domain. The experimental results show the effectiveness of cross-domain transfer learning and the importance of data amount and validate the potential of multistage transfer learning.

Download Full-text

Domain Adaption Based on ELM Autoencoder

Mathematical Problems in Engineering ◽

10.1155/2017/1239164 ◽

2017 ◽

Vol 2017 ◽

pp. 1-8

Author(s):

Wan-Yu Deng ◽

Yu-Tao Qu ◽

Qian Zhang

Keyword(s):

Nonlinear Approximation ◽

Feature Representation ◽

Learning Ability ◽

Alignment Algorithm ◽

Target Domain ◽

Linear Feature ◽

Cross Domain ◽

Domain Adaption ◽

New Space ◽

Subspace Alignment

We propose a new ELM Autoencoder (ELM-AE) based domain adaption algorithm which describes the subspaces of source and target domain by ELM-AE and then carries out subspace alignment to project different domains into a common new space. By leveraging nonlinear approximation ability and efficient one-pass learning ability of ELM-AE, the proposed domain adaption algorithm can efficiently seek a better cross-domain feature representation than linear feature representation approaches such as PCA to improve domain adaption performance. The widely experimental results on Office/Caltech-256 datasets show that the proposed algorithm can achieve better classification accuracy than PCA subspace alignment algorithm and other state-of-the-art domain adaption algorithms in most cases.

Download Full-text

Using Latent Fine-Grained Sentiment for Cross-Domain Sentiment Analysis

International Journal of Knowledge-Based Organizations ◽

10.4018/ijkbo.2021070103 ◽

2021 ◽

Vol 11 (3) ◽

pp. 29-45

Author(s):

Kwun-Ping Lai ◽

Jackie Chun-Sing Ho ◽

Wai Lam

Keyword(s):

Knowledge Transfer ◽

Sentiment Analysis ◽

Real World ◽

Coarse Grained ◽

Target Domain ◽

Training Strategy ◽

Fine Grained ◽

Cross Domain ◽

Proposed Model ◽

Novel Model

The authors investigate the problem task of multi-source cross-domain sentiment classification under the constraint of little labeled data. The authors propose a novel model which is capable of capturing both sentiment terms with strong or weak polarity from various source domains which are useful for knowledge transfer to unlabeled target domain. The authors propose a two-step training strategy with different granularities helping the model to identify sentiment terms with different degrees of sentiment polarity. Specifically, the coarse-grained training step captures the strong sentiment terms from the whole review while the fine-grained training step focuses on the latent fine-grained sentence sentiment which are helpful under the constraint of little labeled data. Experiments on a real-world product review dataset show that the proposed model has a good performance even under the little labeled data constraint.

Download Full-text

Cross-Domain Depression Detection via Harvesting Social Media

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2018/223 ◽

2018 ◽

Cited By ~ 10

Author(s):

Tiancheng Shen ◽

Jia Jia ◽

Guangyao Shen ◽

Fuli Feng ◽

Xiangnan He ◽

...

Keyword(s):

Social Media ◽

Poor Performance ◽

Well Being ◽

Relevant Information ◽

Target Domain ◽

Combination Strategy ◽

Cross Domain ◽

Depression Detection ◽

Improved Performance ◽

Model Training

Depression detection is a significant issue for human well-being. In previous studies, online detection has proven effective in Twitter, enabling proactive care for depressed users. Owing to cultural differences, replicating the method to other social media platforms, such as Chinese Weibo, however, might lead to poor performance because of insufficient available labeled (self-reported depression) data for model training. In this paper, we study an interesting but challenging problem of enhancing detection in a certain target domain (e.g. Weibo) with ample Twitter data as the source domain. We first systematically analyze the depression-related feature patterns across domains and summarize two major detection challenges, namely isomerism and divergency. We further propose a cross-domain Deep Neural Network model with Feature Adaptive Transformation & Combination strategy (DNN-FATC) that transfers the relevant information across heterogeneous domains. Experiments demonstrate improved performance compared to existing heterogeneous transfer methods or training directly in the target domain (over 3.4% improvement in F1), indicating the potential of our model to enable depression detection via social media for more countries with different cultural settings.

Download Full-text