Targeted sentiment classification aims to predict the emotional trend of a specific goal. Currently, most methods (e.g., recurrent neural networks and convolutional neural networks combined with an attention mechanism) are not able to fully capture the semantic information of the context and they also lack a mechanism to explain the relevant syntactical constraints and long-range word dependencies. Therefore, syntactically irrelevant context words may mistakenly be recognized as clues to predict the target sentiment. To tackle these problems, this paper considers that the semantic information, syntactic information, and their interaction information are very crucial to targeted sentiment analysis, and propose an attentional-encoding-based graph convolutional network (AEGCN) model. Our proposed model is mainly composed of multi-head attention and an improved graph convolutional network built over the dependency tree of a sentence. Pre-trained BERT is applied to this task, and new state-of-art performance is achieved. Experiments on five datasets show the effectiveness of the model proposed in this paper compared with a series of the latest models.

The purpose of cross-domain sentiment classification (CDSC) is to fully utilize the rich labeled data in the source domain to help the target domain perform sentiment classification even when labeled data are insufficient. Most of the existing methods focus on obtaining domain transferable semantic information but ignore syntactic information. The performance of BERT may decrease because of domain transfer, and traditional word embeddings, such as word2vec, cannot obtain contextualized word vectors. Therefore, achieving the best results in CDSC is difficult when only BERT or word2vec is used. In this paper, we propose a Dual-word Embedding Model Considering Syntactic Information for Cross-domain Sentiment Classification. Specifically, we obtain dual-word embeddings using BERT and word2vec. After performing BERT embedding, we pay closer attention to semantic information, mainly using self-attention and TextCNN. After word2vec word embedding is obtained, the graph attention network is used to extract the syntactic information of the document, and the attention mechanism is used to focus on the important aspects. Experiments on two real-world datasets show that our model outperforms other strong baselines.

College classes are becoming increasingly large. A critical component in scaling class size is the collaboration and interactions among instructors, teaching assistants, and students. We develop a prototype of anIntelligent Voice Instructor-AssistantSystem (IVIAS)for supportinglargeClasses,in whichAmazon Web Services, Alexa Voice Services and self-developed services are used. It uses ascraping service for reading the questions and answers from the past and current course discussion boards, organizes the questions in JSON format and stored them in thedatabase, which can be accessed by AWS Alexa skills. When a voice question from a student comes, Alexais used fortranslating the voice sentence into texts. Then Siamesedeep LSTM (Long Short-Term Memory)model is introducedto calculate the similarity between the question asked and the questions in the database to find the best-matched answer. Questions with no match will be sent to the instructor, and instructor’s answer will be added into the database. Experiments show that the implemented model achieve promising results that can lead to a practical system. IVIAS starts with a small set of questions. It can grow through learning and improving when more and more questions are asked and answered.