Aspect-­Based Sentiment Analysis (ABSA) is to find the aspects and their corresponding sentiments of a reviewed entity (e.g., a product or service) in various opinion documents (e.g., user reviews), which enables more fine­-grained analysis on the opinion posted by people. ABSA normally involves two main sub­-tasks, namely Aspect Mining (AM) and Aspect Sentiment Classification (ASC). AM sub­-task aims to extract the words describing aspects of a reviewed entity, and the ASC sub-­task is to analyze the expressed sentiments on the aspects. With the rapid application of deep learning technologies, supervised models have recently achieved the best performance on both sub­tasks. However, training these deep models requires a large number of labeled texts which are very costly or unavailable, and they usually perform only one of the two sub-­tasks, which limits their practical use. To this end, in this thesis, we present our research on exploiting semi­supervised learning approaches to address AM and ASC sub-­tasks, which can avoid the heavy requirement on the manual labeling on training data. Moreover, we also propose a new semi­-supervised approach to finish the completed ABSA within a unified framework, thus the two sub-­tasks can be addressed in an end-­to-­end manner.