Probabilistic topic models are statistical methods whose aim is to discover the latent structure in a large collection of documents. The intuition behind topic models is that, by generating documents by latent topics, the word distribution for each topic can be modelled and the prior distribution over the topic learned. In this paper we propose to apply this concept by modelling the topics of sentences for the aspect detection problem in review documents in order to improve sentiment analysis systems. Aspect detection in sentiment analysis helps customers effectively navigate into detailed information about their features of interest. The proposed approach assumes that the aspects of words in a sentence form a Markov chain. The novelty of the model is the extraction of multiword aspects from text data while relaxing the bag-of-words assumption. Experimental results show that the model is indeed able to perform the task significantly better when compared with standard topic models.
Introduction
Despite major advances in our understanding of genetic cardiomyopathies, they remain the leading cause of premature sudden cardiac death and end-stage heart failure in persons under the age of 60 years. Integrated research databases based on a large number of patients may provide a scaffold for future research. Using routine electronic health records and standardised biobanking, big data analysis on a larger number of patients and investigations are possible. In this article, we describe the UNRAVEL research data platform embedded in routine practice to facilitate research in genetic cardiomyopathies.
Design
Eligible participants with proven or suspected cardiac disease and their relatives are asked for permission to use their data and to draw blood for biobanking. Routinely collected clinical data are included in a research database by weekly extraction. A text-mining tool has been developed to enrich UNRAVEL with unstructured data in clinical notes.
Preliminary results
Thus far, 828 individuals with a median age of 57 years have been included, 58% of whom are male. All data are captured in a temporal sequence amounting to a total of 18,565 electrocardiograms, 3619 echocardiograms, data from over 20,000 radiological examinations and 650,000 individual laboratory measurements.
Conclusion
Integration of routine electronic health care in a research data platform allows efficient data collection, including all investigations in chronological sequence. Trials embedded in the electronic health record are now possible, providing cost-effective ways to answer clinical questions. We explicitly welcome national and international collaboration and have provided our protocols and other materials on
www.unravelrdp.nl
.
With the rapid growth of user-generated content on the internet, sentiment analysis of online reviews has become a hot research topic recently, but due to variety and wide range of products and services, the supervised and domainspecific models are often not practical. As the number of reviews expands, it is essential to develop an efficient sentiment analysis model that is capable of extracting product aspects and determining the sentiments for aspects. In this paper, we propose an unsupervised model for detecting aspects in reviews. In this model, first a generalized method is proposed to learn multi-word aspects. Second, a set of heuristic rules is employed to take into account the influence of an opinion word on detecting the aspect. Third a new metric based on mutual information and aspect frequency is proposed to score aspects with a new bootstrapping iterative algorithm. The presented bootstrapping algorithm works with an unsupervised seed set. Finally two pruning methods based on the relations between aspects in reviews are presented to remove incorrect aspects. The proposed model does not require labeled training data and can be applicable to other languages or domains. We demonstrate the effectiveness of our model on a collection of product reviews dataset, where it outperforms other techniques.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.