Results: We evaluated several state-of-the-art text classification algorithms as well as our dependency tree–based classifier algorithm on a real-world doctor review dataset.
Specifically, our algorithm automatically extracts dependency tree patterns and uses them to classify review sentences. Then we proposed a new algorithm that goes beyond bag-of-words or deep learning classification techniques by leveraging natural language processing (NLP) tools. Methods: We first manually examined a large number of reviews to extract a set of features that are frequently mentioned in the reviews.
These methods are evaluated on their accuracy to classify a diverse set of doctor review features. Objective: This study aimed to adapt existing and propose novel text classification methods on the domain of doctor reviews. However, in the domain of doctor reviews, this setting is too restrictive: a feature such as visit duration for doctor reviews may be expressed in many ways and does not necessarily have a positive or negative sentiment. Most previous work on automatic analysis of Web-based customer reviews assumes that (1) product features are described unambiguously by a small number of keywords, for example, battery for phones and (2) the opinion for each feature has a positive or negative sentiment. These reviews address a diverse set of topics (features), including wait time, office staff, doctor’s skills, and bedside manners. Asian/Pacific Island Nursing Journal 10 articlesĭepartment of Computer Science and EngineeringĮmail: An increasing number of doctor reviews are being generated by patients on the internet.JMIR Bioinformatics and Biotechnology 32 articles.JMIR Biomedical Engineering 68 articles.Journal of Participatory Medicine 78 articles.JMIR Perioperative Medicine 89 articles.JMIR Rehabilitation and Assistive Technologies 201 articles.JMIR Pediatrics and Parenting 279 articles.Interactive Journal of Medical Research 306 articles.JMIR Public Health and Surveillance 1141 articles.Journal of Medical Internet Research 7471 articles.
0 kommentar(er)
