Word2Vec and Doc2Vec in Unsupervised Sentiment Analysis of Clinical\n Discharge Summaries

2018/05/01 by Qufei Chen, Chen, Qufei, Marina Sokolova +1 · 1 citation
Computer Science · #68T05 #68T50 #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning in Healthcare #Sentiment Analysis and Opinion Mining #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1805.00352

openalex publication_date 2018/05/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

In this study, we explored application of Word2Vec and Doc2Vec for sentiment\nanalysis of clinical discharge summaries. We applied unsupervised learning\nsince the data sets did not have sentiment annotations. Note that unsupervised\nlearning is a more realistic scenario than supervised learning which requires\nan access to a training set of sentiment-annotated data. We aim to detect if\nthere exists any underlying bias towards or against a certain disease. We used\nSentiWordNet to establish a gold sentiment standard for the data sets and\nevaluate performance of Word2Vec and Doc2Vec methods. We have shown that the\nWord2vec and Doc2Vec methods complement each other results in sentiment\nanalysis of the data sets.\n

Cited by

• Tweets Sentiment Analysis via Word Embeddings and Machine Learning Techniques

Related

• Sentiment Analysis of Citations Using Word2vec
• Distinguishing Clinical Sentiment: The Importance of Domain Adaptation\n in Psychiatric Patient Health Records
• Natural Language Processing, Sentiment Analysis and Clinical Analytics
• Prediction Using Note Text: Synthetic Feature Creation with word2vec
• Sentiment Analysis in Drug Reviews using Supervised Machine Learning Algorithms