사례분석: 도서(book) 데이터에 적용

data.test <- read.csv('books_test.csv', stringsAsFactors = F)
corpus <- Corpus(VectorSource(data.test$Texts))
dtm.test <- DocumentTermMatrix(corpus,
                               control = list(tolower = T,
                                              removePunctuation = T,
                                              removeNumbers = T,
                                              stopwords = stopwords("SMART"),
                                              weighting = weightTfIdf,
                                              dictionary = Terms(dtm)))

library(tm.plugin.sentiment)
senti.lm.test <- polarity(dtm.test, names(pos.lm), names(neg.lm))
senti.lasso.test <- polarity(dtm.test, names(pos.lasso), names(neg.lasso))
senti.ridge.test <- polarity(dtm.test, names(pos.ridge), names(neg.ridge))
senti.elastic.test <- polarity(dtm.test, names(pos.elastic), names(neg.elastic))

senti.lm.b.test <- ifelse(senti.lm.test > 0, 1, 0)
senti.lasso.b.test <- ifelse(senti.lasso.test > 0, 1, 0)
senti.ridge.b.test <- ifelse(senti.ridge.test > 0, 1, 0)
senti.elastic.b.test <- ifelse(senti.elastic.test > 0, 1, 0)

library(caret)
confusionMatrix(senti.lm.b.test, data.test$Sentiment)
confusionMatrix(senti.lasso.b.test, data.test$Sentiment
confusionMatrix(senti.ridge.b.test, data.test$Sentiment)
confusionMatrix(senti.elastic.b.test, data.test$Sentiment)

## 모바일폰

data.test <- read.csv('mobile2014_test.csv', stringsAsFactors = F)
corpus <- Corpus(VectorSource(data.test$Texts))
dtm.test <- DocumentTermMatrix(corpus,
                               control = list(tolower = T,
                                              removePunctuation = T,
                                              removeNumbers = T,
                                              stopwords = stopwords("SMART"),
                                              weighting = weightTfIdf,
                                              dictionary = Terms(dtm)))

library(tm.plugin.sentiment)
senti.lm.test <- polarity(dtm.test, names(pos.lm), names(neg.lm))
senti.lasso.test <- polarity(dtm.test, names(pos.lasso), names(neg.lasso))
senti.ridge.test <- polarity(dtm.test, names(pos.ridge), names(neg.ridge))
senti.elastic.test <- polarity(dtm.test, names(pos.elastic), names(neg.elastic))

senti.lm.b.test <- ifelse(senti.lm.test > 0, 1, 0)
senti.lasso.b.test <- ifelse(senti.lasso.test > 0, 1, 0)
senti.ridge.b.test <- ifelse(senti.ridge.test > 0, 1, 0)
senti.elastic.b.test <- ifelse(senti.elastic.test > 0, 1, 0)

lm.acc <- confusionMatrix(senti.lm.b.test, data.test$Sentiment)$overall[1]
lasso.acc <- confusionMatrix(senti.lasso.b.test, data.test$Sentiment)$overall[1]
ridge.acc <- confusionMatrix(senti.ridge.b.test, data.test$Sentiment)$overall[1]
elastic.acc <- confusionMatrix(senti.elastic.b.test, data.test$Sentiment)$overall[1]
acc <- c(lm.acc, lasso.acc, ridge.acc, elastic.acc)
names(acc) <- c('lm', 'lasso', 'ridge', 'elastic')

mobile.acc <- acc

## 태블릿
data.test <- read.csv('tablet2014_test.csv', stringsAsFactors = F)
corpus <- Corpus(VectorSource(data.test$Texts))
dtm.test <- DocumentTermMatrix(corpus,
                               control = list(tolower = T,
                                              removePunctuation = T,
                                              removeNumbers = T,
                                              stopwords = stopwords("SMART"),
                                              weighting = weightTfIdf,
                                              dictionary = Terms(dtm)))

library(tm.plugin.sentiment)
senti.lm.test <- polarity(dtm.test, names(pos.lm), names(neg.lm))
senti.lasso.test <- polarity(dtm.test, names(pos.lasso), names(neg.lasso))
senti.ridge.test <- polarity(dtm.test, names(pos.ridge), names(neg.ridge))
senti.elastic.test <- polarity(dtm.test, names(pos.elastic), names(neg.elastic))

senti.lm.b.test <- ifelse(senti.lm.test > 0, 1, 0)
senti.lasso.b.test <- ifelse(senti.lasso.test > 0, 1, 0)
senti.ridge.b.test <- ifelse(senti.ridge.test > 0, 1, 0)
senti.elastic.b.test <- ifelse(senti.elastic.test > 0, 1, 0)

lm.acc <- confusionMatrix(senti.lm.b.test, data.test$Sentiment)$overall[1]
lasso.acc <- confusionMatrix(senti.lasso.b.test, data.test$Sentiment)$overall[1]
ridge.acc <- confusionMatrix(senti.ridge.b.test, data.test$Sentiment)$overall[1]
elastic.acc <- confusionMatrix(senti.elastic.b.test, data.test$Sentiment)$overall[1]
acc <- c(lm.acc, lasso.acc, ridge.acc, elastic.acc)
names(acc) <- c('lm', 'lasso', 'ridge', 'elastic')

tablet.acc <- acc

## 도서

data.test <- read.csv('books_test.csv', stringsAsFactors = F)
corpus <- Corpus(VectorSource(data.test$Texts))
dtm.test <- DocumentTermMatrix(corpus,
                               control = list(tolower = T,
                                              removePunctuation = T,
                                              removeNumbers = T,
                                              stopwords = stopwords("SMART"),
                                              weighting = weightTfIdf,
                                              dictionary = Terms(dtm)))

library(tm.plugin.sentiment)
senti.lm.test <- polarity(dtm.test, names(pos.lm), names(neg.lm))
senti.lasso.test <- polarity(dtm.test, names(pos.lasso), names(neg.lasso))
senti.ridge.test <- polarity(dtm.test, names(pos.ridge), names(neg.ridge))
senti.elastic.test <- polarity(dtm.test, names(pos.elastic), names(neg.elastic))

senti.lm.b.test <- ifelse(senti.lm.test > 0, 1, 0)
senti.lasso.b.test <- ifelse(senti.lasso.test > 0, 1, 0)
senti.ridge.b.test <- ifelse(senti.ridge.test > 0, 1, 0)
senti.elastic.b.test <- ifelse(senti.elastic.test > 0, 1, 0)

lm.acc <- confusionMatrix(senti.lm.b.test, data.test$Sentiment)$overall[1]
lasso.acc <- confusionMatrix(senti.lasso.b.test, data.test$Sentiment)$overall[1]
ridge.acc <- confusionMatrix(senti.ridge.b.test, data.test$Sentiment)$overall[1]
elastic.acc <- confusionMatrix(senti.elastic.b.test, data.test$Sentiment)$overall[1]
acc <- c(lm.acc, lasso.acc, ridge.acc, elastic.acc)
names(acc) <- c('lm', 'lasso', 'ridge', 'elastic')

book.acc <- acc

## 정확도 비교

mobile.acc
tablet.acc
book.acc