Domain Adaptation Using a Combination of Multiple Embeddings for Sentiment Analysis
Hiroyuki Shinnou, Xinyu Zhao, Kanako Komiya · Institutional Repositories DataBase (IRDB) · 2018
We propose a new method for domain adaptation by using a combination of multiple embeddings for sentiment analysis.We first make the following embeddings for the document: (1) vector construction by using the bag-of-words model, (2) vector by dimension reduction using SVD, and (3) embedded vector by using doc2vec.We then connect the three embeddings.This connected vector is used as the feature vector in the learning and testing stages.In the experiment, we used an Amazon dataset that has three domains ("books", "DVD" and "music") and six types of domain adaptations.The experiment showed the effectiveness of our proposed method.