Information geometry enhanced fuzzy deep belief networks for sentiment classification
- PDF / 2,116,766 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 77 Downloads / 227 Views
ORIGINAL ARTICLE
Information geometry enhanced fuzzy deep belief networks for sentiment classification Meng Wang1 · Zhen‑Hu Ning1 · Tong Li1 · Chuang‑Bai Xiao1 Received: 2 May 2018 / Accepted: 26 December 2018 © Springer-Verlag GmbH Germany, part of Springer Nature 2019
Abstract With the development of internet, more and more people share reviews. Efficient sentiment analysis over such reviews using deep learning techniques has become an emerging research topic, which has attracted more and more attention from the natural language processing community. However, improving performance of a deep neural network remains an open question. In this paper, we propose a sophisticated algorithm based on deep learning, fuzzy clustering and information geometry. In particular, the distribution of training samples is treated as prior knowledge and is encoded in fuzzy deep belief networks using an improved Fuzzy C-Means (FCM) clustering algorithm. We adopt information geometry to construct geodesic distance between the distributions over features for classification, improving the FCM. Based on the clustering results, we then embed the fuzzy rules learned by FCM into fuzzy deep belief networks in order to improve their performance. Finally, we evaluate our proposal using empirical data sets that are dedicated for sentiment classification. The results show that our algorithm brings out significant improvement over existing methods. Keywords Fuzzy neural networks · Information geometry · Semi-supervised learning · Sentiment classification
1 Introduction Due to the fast development of internet, various smart appliances have play more and more important roles in our daily life, such as Apple watch, smart car etc. In particular, people can easily express their opinions through their smart appliances in different ways. As a result, it is not surprising that nowadays there are tons of reviews available out there. Sentiment classification aims to determine the attitude of a speaker with respect to some topic or the overall contextual polarity of a document, such as ‘positive’ or ‘negative’,’thumbs up’ or ‘thumbs down’ [1]. Efficiently and precisely analyzing sentiments is useful for sensing public’s * Zhen‑Hu Ning [email protected] Meng Wang [email protected] Tong Li [email protected] Chuang‑Bai Xiao [email protected] 1
Faculty of Information Technology, Beijing University of Technology, Beijing 100124, People’s Republic of China
opinions on various topics, which has wide applications in both academic and industrial fields. As a result, sentiment classification for the aforementioned reviews nowadays has attracted more and more attention from the natural language processing (NLP) community. Methods for document sentiment classification are generally based on lexicon and corpus. Lexicon-based approaches can derive a sentiment measure for text based on sentiment lexicons [2]. Corpus-based approaches involve a statistical classification method [3]. The corpus-based approaches usually outperform the lexicon-based approaches and ha
Data Loading...
