Open AccessDiscovery of Probable Sentiments in Hypertensive Pregnant Women using Horizontal Fragmentation and Pointwise Mutual Information
Author(s) -
Sudhir Tirumalasetty,
P. Tejaswini,
R Renuka,
M Naga Sirisha
Publication year - 2019
Publication title -
international journal of scientific research in computer science, engineering and information technology
Language(s) - English
Resource type - Journals
ISSN - 2456-3307
DOI - 10.32628/cseit1952191
Subject(s) - sentence , pointwise mutual information , sentiment analysis , phrase , context (archaeology) , pointwise , noun phrase , computer science , health care , psychology , data science , natural language processing , mutual information , artificial intelligence , political science , mathematics , noun , history , mathematical analysis , archaeology , law
Since a decade research over sentiment analysis and opinion mining was evolving slowing and emerging widely with greater perspectives and objectives. Sentiment analysis is an important task in order to gain insights over the huge amounts of opinions that are generated on a daily basis. This analysis relies on the opinions made by the individuals. These opinions are text, may be positive or negative or a phrase which gives significance to the context. Also these opinions have the power of expressing the context besides drags the attention of new folks. Expressing such opinions ranges from documents level, to the sentence level, to phrase level, to word level and to special symbol level. All these opinion types are labelled with common name Sentiment Analysis. Sentiment Analysis is health care is evolving narrowly with wider research strings. This paper mainly focuses in identifying Sentiments in health care. These sentiments can be medical test values which may be numeric and nominal; sometimes in text too. Such sentiments are identified with pre-fragmentation of data set and Pointwise Mutual Information measure. To accomplish this data of hypertensive pregnant women is considered.