Hidden Topic Models for Multi-label Review Classification: An Experimental Study
نویسندگان
چکیده
In recent years, Multi-Label Classification (MLC) becomes an important task in the field of Supervised Learning. The MLC tasks are omnipresent in real-world problems, in which an instance could belong simultaneously to different classes. In this paper, an MLC model experimental study on user reviews on Vietnamese hotels is showed. We enriched the data features by using a hidden topic method for short documents of user reviews. We also used mutual information for feature selection. Experiments on user reviews on about one thousand Vietnamese hotels are showed.
منابع مشابه
Gibbs max-margin topic models with data augmentation
Max-margin learning is a powerful approach to building classifiers and structured output predictors. Recent work on max-margin supervised topic models has successfully integrated it with Bayesian topic models to discover discriminative latent semantic structures and make accurate predictions for unseen testing data. However, the resulting learning problems are usually hard to solve because of t...
متن کاملExploiting Associations between Class Labels in Multi-label Classification
Multi-label classification has many applications in the text categorization, biology and medical diagnosis, in which multiple class labels can be assigned to each training instance simultaneously. As it is often the case that there are relationships between the labels, extracting the existing relationships between the labels and taking advantage of them during the training or prediction phases ...
متن کاملMLIFT: Enhancing Multi-label Classifier with Ensemble Feature Selection
Multi-label classification has gained significant attention during recent years, due to the increasing number of modern applications associated with multi-label data. Despite its short life, different approaches have been presented to solve the task of multi-label classification. LIFT is a multi-label classifier which utilizes a new strategy to multi-label learning by leveraging label-specific ...
متن کاملA systematic review on experimental multi - label learning
Multi-label learning deals with the classification problem where each example is associated with a set of labels, which are usually dependent. This research topic has emerged in recent years due to the increasing number of applications where examples are annotated with more than one label. However, there is a lack of reviews focusing on pieces of work which report experimental results for multi...
متن کاملA Joint Semantic Vector Representation Model for Text Clustering and Classification
Text clustering and classification are two main tasks of text mining. Feature selection plays the key role in the quality of the clustering and classification results. Although word-based features such as term frequency-inverse document frequency (TF-IDF) vectors have been widely used in different applications, their shortcoming in capturing semantic concepts of text motivated researches to use...
متن کامل