201218_Why_EduPsy

教育心理学を学ぶ理由とは

塾生による自由記述\((n=17)\)

単語の出現頻度

とりあえず全部

res.wdfq.1 <- RMeCabFreq("WhyEduPsy.txt")

## file = WhyEduPsy.txt 
## length = 579

DT::datatable(res.wdfq.1)

品詞を名詞，動詞，形容詞に限定

res.wdfq.2 <- docDF("WhyEduPsy.txt", type=1, pos = c("名詞", "動詞", "形容詞"))

## file_name =  ./WhyEduPsy.txt opened
## number of extracted terms = 458
## now making a data frame. wait a while!

DT::datatable(res.wdfq.2)

一部の単語を除外 + 品詞を名詞，動詞，形容詞に限定

res.wdfq.30 <- docDF("WhyEduPsy.txt", type=1, pos = c("名詞", "動詞", "形容詞"))

## file_name =  ./WhyEduPsy.txt opened
## number of extracted terms = 458
## now making a data frame. wait a while!

stopword <- c("ある", "いう", "いく", "いける", "いる", "うる", "おく", "おる", "かや", "く", "くる", "くれる", "ここ", "こと ", "これ", "これら", "さ", "しまう", "しれる", "する", "せる", "それ", "たち", "ため", "つぎ", "つく", "どれ", "ない", "なさる", "なに", "なる", "なん", "の", "はず", "もの", "もみ", "よう", "られる", "れる", "一" )
res.wdfq.3 <- subset(res.wdfq.30, !(TERM %in% stopword))

# 多い順に表示
DT::datatable(res.wdfq.3[order(res.wdfq.3$WhyEduPsy.txt,decreasing = TRUE),])

単語の共起

品詞を名詞，動詞，形容詞に限定

library(igraph)

## 
## Attaching package: 'igraph'

## The following objects are masked from 'package:stats':
## 
##     decompose, spectrum

## The following object is masked from 'package:base':
## 
##     union

res.cooc.10 <- NgramDF("WhyEduPsy.txt", type=1, pos = c("名詞", "動詞", "形容詞"))

## file = WhyEduPsy.txt Ngram = 2

res.cooc.11 <- subset(res.cooc.10,!(Ngram1 %in% stopword) & !(Ngram2 %in% stopword))
g <- graph.data.frame(res.cooc.11, directed = FALSE)
plot(g, vertex.size = 6, vertex.label.family="HiraKakuProN-W3", 
vertex.label = V(g)$name, vertex.color = "yellow")

一部の単語を除外 + 品詞を名詞，動詞，形容詞に限定

共起頻度2以上に限定

「教職過程に就く者」という表現を除外（出題内容の繰り返しのため）

library(igraph)
res.cooc.20 <- NgramDF("WhyEduPsy.txt", type=1, pos = c("名詞", "動詞", "形容詞"))

## file = WhyEduPsy.txt Ngram = 2

stopword <- c("ある", "いう", "いく", "いける", "いる", "うる", "おく", "おる", "かや", "く", "くる", "くれる", "ここ", "こと ", "これ", "これら", "さ", "しまう", "しれる", "する", "せる", "それ", "たち", "ため", "つぎ", "つく", "どれ", "ない", "なさる", "なに", "なる", "なん", "の", "はず", "もの", "もみ", "よう", "られる", "れる", "一" , "教職", "過程", "就く", "者")
res.cooc.21 <- subset(res.cooc.20,!(Ngram1 %in% stopword) & !(Ngram2 %in% stopword))
res.cooc.21 <- subset(res.cooc.21, Freq > 1)
g <- graph.data.frame(res.cooc.21, directed = FALSE)
plot(g, vertex.size = 3, vertex.label.cex = 0.6, 
     vertex.label.family="HiraKakuProN-W3", 
     vertex.label = V(g)$name, vertex.color = "yellow")