Predicting Online Doctor Ratings from User Reviews Using Convolutional Neural Networks

Sharma, Ranti Dev; Tripathi, Samarth; Sahu, Sunil Kumar; Mittal, Sudhanshu; Anand, Ashish

doi:10.18178/ijmlc.2016.6.2.590

Cited by 19 publications

(9 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the manual nature of the content analysis makes it very hard to process large amounts of reviews, which is another challenge of the information age. The third approach is the algorithm or data-driven approach [ 9 , 20 , 21 ]; for example, Hao and Zhang [ 9 ] applied the topic extraction algorithm LDA to >500,000 textual reviews from >75,000 Chinese doctors across 4 major specialty areas to identify the dimensions inside the physician reviews. However, the output of the algorithm usually depends on the data, and many categories are hard to explain in medical practice.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Developing Embedded Taxonomy and Mining Patients’ Interests From Web-Based Physician Reviews: Mixed-Methods Approach

Jia¹,

Liu²,

Li³

et al. 2018

J Med Internet Res

View full text Add to dashboard Cite

BackgroundWeb-based physician reviews are invaluable gold mines that merit further investigation. Although many studies have explored the text information of physician reviews, very few have focused on developing a systematic topic taxonomy embedded in physician reviews. The first step toward mining physician reviews is to determine how the natural structure or dimensions is embedded in reviews. Therefore, it is relevant to develop the topic taxonomy rigorously and systematically.ObjectiveThis study aims to develop a hierarchical topic taxonomy to uncover the latent structure of physician reviews and illustrate its application for mining patients’ interests based on the proposed taxonomy and algorithm.MethodsData comprised 122,716 physician reviews, including reviews of 8501 doctors from a leading physician review website in China (haodf.com), collected between 2007 and 2015. Mixed methods, including a literature review, data-driven-based topic discovery, and human annotation were used to develop the physician review topic taxonomy.ResultsThe identified taxonomy included 3 domains or high-level categories and 9 subtopics or low-level categories. The physician-related domain included the categories of medical ethics, medical competence, communication skills, medical advice, and prescriptions. The patient-related domain included the categories of the patient profile, symptoms, diagnosis, and pathogenesis. The system-related domain included the categories of financing and operation process. The F-measure of the proposed classification algorithm reached 0.816 on average. Symptoms (Cohen d=1.58, Δu=0.216, t=229.75, and P<.001) are more often mentioned by patients with acute diseases, whereas communication skills (Cohen d=−0.29, Δu=−0.038, t=−42.01, and P<.001), financing (Cohen d=−0.68, Δu=−0.098, t=−99.26, and P<.001), and diagnosis and pathogenesis (Cohen d=−0.55, Δu=−0.078, t=−80.09, and P<.001) are more often mentioned by patients with chronic diseases. Patients with mild diseases were more interested in medical ethics (Cohen d=0.25, Δu 0.039, t=8.33, and P<.001), operation process (Cohen d=0.57, Δu 0.060, t=18.75, and P<.001), patient profile (Cohen d=1.19, Δu 0.132, t=39.33, and P<.001), and symptoms (Cohen d=1.91, Δu=0.274, t=62.82, and P<.001). Meanwhile, patients with serious diseases were more interested in medical competence (Cohen d=−0.99, Δu=−0.165, t=−32.58, and P<.001), medical advice and prescription (Cohen d=−0.65, Δu=−0.082, t=−21.45, and P<.001), financing (Cohen d=−0.26, Δu=−0.018, t=−8.45, and P<.001), and diagnosis and pathogenesis (Cohen d=−1.55, Δu=−0.229, t=−50.93, and P<.001).ConclusionsThis mixed-methods approach, integrating literature reviews, data-driven topic discovery, and human annotation, is an effective and rigorous way to develop a physician review topic taxonomy. The proposed algorithm based on Labeled-Latent Dirichlet Allocation can achieve impressive classification results for mining patients’ interests. Furthermore, the mining results reveal marked differences in patients’ inter...

show abstract

Section: Discussionmentioning

confidence: 99%

“…Finally, we ranked the papers based on the score. After scoring each paper, we identified 7 relevant papers whose scores were >20 [ 20 - 26 ]. The 7 papers were carefully reviewed to identify the potential topics.…”

Section: Methodsmentioning

confidence: 99%

Developing Embedded Taxonomy and Mining Patients’ Interests From Web-Based Physician Reviews: Mixed-Methods Approach

Jia¹,

Liu²,

Li³

et al. 2018

J Med Internet Res

View full text Add to dashboard Cite

show abstract

“…These representation models encode the linguistic properties of words in a form where semantically similar words appear closely in vector space. They have proved highly popular and successful for many NLP tasks, including named entity recognition [20–22, 43], event identification [44], relation extraction [45] and text classification [23, 24]. Among them, the skip-gram model with negative sampling (SGNS, [46]) has achieved cutting-edge results in a range of semantic tasks such as sentence completion and analogy [46, 47].…”

Section: Related Workmentioning

confidence: 99%

“…We encode word features into a low-dimensional space using neural networks [17–19]. Neural word representations (embeddings) serve now as invaluable features in a broad range of NLP tasks, including named entity recognition [20–22] and text classification [23, 24]. Neural representation models such as the skip-gram model with negative sampling (SGNS) are highly efficient in capturing syntactic and semantic properties of words in corpora and are therefore intuitively useful also for VerbNet-style classification [25].…”

Section: Introductionmentioning

confidence: 99%

A neural classification method for supporting the creation of BioVerbNet

et al. 2019

View full text Add to dashboard Cite

BackgroundVerbNet, an extensive computational verb lexicon for English, has proved useful for supporting a wide range of Natural Language Processing tasks requiring information about the behaviour and meaning of verbs. Biomedical text processing and mining could benefit from a similar resource. We take the first step towards the development of BioVerbNet: A VerbNet specifically aimed at describing verbs in the area of biomedicine. Because VerbNet-style classification is extremely time consuming, we start from a small manual classification of biomedical verbs and apply a state-of-the-art neural representation model, specifically developed for class-based optimization, to expand the classification with new verbs, using all the PubMed abstracts and the full articles in the PubMed Central Open Access subset as data.ResultsDirect evaluation of the resulting classification against BioSimVerb (verb similarity judgement data in biomedicine) shows promising results when representation learning is performed using verb class-based contexts. Human validation by linguists and biologists reveals that the automatically expanded classification is highly accurate. Including novel, valid member verbs and classes, our method can be used to facilitate cost-effective development of BioVerbNet.ConclusionThis work constitutes the first effort on applying a state-of-the-art architecture for neural representation learning to biomedical verb classification. While we discuss future optimization of the method, our promising results suggest that the automatic classification released with this article can be used to readily support application tasks in biomedicine.Electronic supplementary materialThe online version of this article (10.1186/s13326-018-0193-x) contains supplementary material, which is available to authorized users.

show abstract

“…which can extract a hierarchical representation of invariant input data transformations and scales [8], which has achieved high accuracy in classifying the grading of palm oil Fresh Fruit Bunch (FFB) ripeness [8]. Besides that, CNN is also capable of producing high accuracy in classifying patients review towards doctors and healthcare services [9]. Meanwhile, AlexNet has proven to obtain excellent performance for ear recognition [10].…”

mentioning

confidence: 99%

Evaluation of Basic Convolutional Neural Network, AlexNet and Bag of Features for Indoor Object Recognition

Zulkeflie¹,

Fammy²,

İbrahim³

et al. 2019

IJMLC

View full text Add to dashboard Cite

This paper evaluates two deep learning techniques that are basic Convolutional Neural Network (CNN) and AlexNet along with a classical local descriptor that is Bag of Features (BoF) with Speeded-Up Robust Feature (SURF) and Support Vector Machine (SVM) classifier for indoor object recognition. A publicly available dataset, MCIndoor20000, has been used in this experiment that consists of doors, signage, and stairs images of Marshfield Clinic. Experimental results indicate that AlexNet achieves the highest accuracy followed by basic CNN and BoF. Furthermore, the results also show that BoF, a machine learning technique, can also produce a high accuracy performance as basic CNN, a deep learning technique, for image recognition.

show abstract

Predicting Online Doctor Ratings from User Reviews Using Convolutional Neural Networks

Cited by 19 publications

References 11 publications

Developing Embedded Taxonomy and Mining Patients’ Interests From Web-Based Physician Reviews: Mixed-Methods Approach

Developing Embedded Taxonomy and Mining Patients’ Interests From Web-Based Physician Reviews: Mixed-Methods Approach

A neural classification method for supporting the creation of BioVerbNet

Evaluation of Basic Convolutional Neural Network, AlexNet and Bag of Features for Indoor Object Recognition

Contact Info

Product

Resources

About