Cheng’s Dissertation

Qualitative EQTA

Session 1: Prepare for the analysis

## Load the R packages
# For text mining
library(tm)

## Loading required package: NLP

# For use the pipe sign
library(dplyr)

## Warning: package 'dplyr' was built under R version 4.1.2

## 
## Attaching package: 'dplyr'

## The following objects are masked from 'package:stats':
## 
##     filter, lag

## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union

# For plot
library(ggplot2)

## Warning: package 'ggplot2' was built under R version 4.1.2

## 
## Attaching package: 'ggplot2'

## The following object is masked from 'package:NLP':
## 
##     annotate

# For wordcoloud
library(wordcloud)

## Loading required package: RColorBrewer

## Warning: package 'RColorBrewer' was built under R version 4.1.2

# For pyramid plot
library(plotrix)
# For word network
library(qdap)

## Loading required package: qdapDictionaries

## Loading required package: qdapRegex

## Warning: package 'qdapRegex' was built under R version 4.1.2

## 
## Attaching package: 'qdapRegex'

## The following object is masked from 'package:ggplot2':
## 
##     %+%

## The following object is masked from 'package:dplyr':
## 
##     explain

## Loading required package: qdapTools

## 
## Attaching package: 'qdapTools'

## The following object is masked from 'package:dplyr':
## 
##     id

## 
## Attaching package: 'qdap'

## The following objects are masked from 'package:tm':
## 
##     as.DocumentTermMatrix, as.TermDocumentMatrix

## The following object is masked from 'package:NLP':
## 
##     ngrams

## The following objects are masked from 'package:base':
## 
##     Filter, proportions

# For primaid plot
library(plotrix)
## Load the data
library(readxl)

## Warning: package 'readxl' was built under R version 4.1.2

Load the dataset

MM_Data <- read_excel("MM Dissertation Coding Table(AutoRecovered).xlsx", 
    sheet = "Data Coding for EQTA")

Session 2: Descriptive Data Analysis on Basic Paper Information

Article Numbers by Years

MM_article_by_year <- MM_Data %>%
  group_by(Year) %>% 
  count()
p <- ggplot(MM_article_by_year,aes(x=Year,y=n))+geom_line()+ggtitle("Article Frequency by Year")+ylab('Frequency')
p + theme(
  panel.background = element_rect(fill = "White",
                                  colour = "White",
                                  size = 0.5, linetype = "solid"),
  panel.grid.major = element_line(size = 0.25, linetype = 'solid',
                                  colour = "Grey"), 
  panel.grid.minor = element_line(size = 0.25, linetype = 'solid',
                                  colour = "Grey")
)

sum(MM_Data$`Author N`)

## [1] 294

mean(MM_Data$`Author N`)

## [1] 2.60177

sd(MM_Data$`Author N`)

## [1] 1.567185

Takeouts:

-1, It looks like every a few years, there is a heated trend for Mind Map research.

Most Popular Mind Map Author

head(sort(table(MM_Data$`1st Author`),decreasing=TRUE),10)

## 
##  Anthony V. D’Antoni       Ivana Simonova     Cheryl L. Willis 
##                    4                    3                    2 
##    Johannes Wheeldon        Aan Yuliyanto  Alma Prima Nurlaila 
##                    2                    1                    1 
##       Alper Yorulmaz       Amber Franklin Amila Wickramasinghe 
##                    1                    1                    1 
##  Ana Daniela Chistea 
##                    1

Takeouts:

No.1 Anthony V. D’Antoni (4 articles)

No.2 Ivana Simonova (3 articles)

No.3 Cheryl L. Willis & Johannes Wheeldon (2 articles)

Mind Map by Author Numbers

# Pool the data
MM_Author <- MM_Data[,c(2,5,6)]
mean(MM_Author$`Author N`)

## [1] 2.60177

sd(MM_Author$`Author N`)

## [1] 1.567185

table(MM_Author$`Author N`)

## 
##  1  2  3  4  5  6  7 
## 34 29 24  9 11  3  3

MM_Author[which(MM_Author$`Author N`==max(MM_Author$`Author N`)),]

## # A tibble: 3 × 3
##   `Article Topic`                                        `1st Author` `Author N`
##   <chr>                                                  <chr>             <dbl>
## 1 What Are The Major Curriculum Issues?: The Use Of Min… Fersun Payk…          7
## 2 Patient education in rheumatoid arthritis: the effect… D. Walker             7
## 3 Computer‑aided mind map generation via crowdsourcing … Bradley Cam…          7

hist(MM_Author$`Author N`)

Takeouts:

1, Most of the Mind Map research are conducted by less than three authors.

2, Three Mind Map research has seven authors.

A, Patient education in rheumatoid arthritis: the effectiveness of the ARC booklet and the mind map. First Author: D. Walker
B, What Are The Major Curriculum Issues?: The Use Of Mindmapping As A Brainstorming Exercise. First Author: Fersun Paykoc.
C, Computer‑aided mind map generation via crowdsourcing and machine learning. First Author: Bradley Camburn.

Mind Map Studies by Country

# How many counties?
unique(MM_Data$`Country of Authorship`) # 113 Research from 31 Country

##  [1] "United States"        "United Kingdom"       "Finland"             
##  [4] "Sweden"               "Turkey"               "Switzerland"         
##  [7] "French"               "Canada"               "China"               
## [10] "Romania"              "Austria"              "Taiwan"              
## [13] "Malaysia"             "Sri Lanka"            "Iran"                
## [16] "Australia"            "Bangladesh"           "Thailand"            
## [19] "Indonesia"            "Belgium"              "Czech Republic"      
## [22] "Russia"               "India"                "Egypt"               
## [25] "United Arab Emirates" "Pakistan"             "Netherlands"         
## [28] "Perú"                 "Japan"                "Uzbekistan"          
## [31] "Brazil"

head(sort(table(MM_Data$`Country of Authorship`),decreasing=TRUE),5)

## 
##  United States          China         Turkey Czech Republic      Indonesia 
##             28             14              8              6              6

Countries with the most Mind Map studies.

United States: 28 Studies
China: 14 Studies
Turkey: 8 Studies
Czech Republic: 6 Studies
Indonesia: 6 Studies

Session 3: WordCoulds for making the categories

Preparing the data cleaning

clean_corpus <- function(corpus) {
  # Remove punctuation
  corpus <- tm_map(corpus, removePunctuation)
  # Transform to lower case
  corpus <- tm_map(corpus, content_transformer(tolower))
  # Add more stopwords
  corpus <- tm_map(corpus, removeWords, words = c(stopwords("en"),"using","used","two","can","will","article","paper","study","provide","provides","provided","across","based","within","found","data","three","set","use","results","variables","single","first","one","second","third","number","students","however","also","well","may","purpose","showed"))
  # Strip white space
  corpus <- tm_map(corpus,stripWhitespace)
  return(corpus)
}

Dealing with more stop words and duplicate words

# Replace the duplicate words
MM_Data$`Article Topic` <- gsub("Maps","map",MM_Data$`Article Topic`)

What’s the common terms for the target articles? (Only Title)

# Make a vector source from titles
Title_source <- VectorSource(MM_Data$`Article Topic`)
# Make a volatile corpus from Title_source
Title_corpus <- VCorpus(Title_source)
# Clean the corpus
clean_Title <- clean_corpus(Title_corpus)
# Create a term-document matrix from the corpus
Title_tdm <- TermDocumentMatrix(clean_Title)
# Convert coffee_tdm to a matrix
Title_m <- as.matrix(Title_tdm)
# Calculate the row sums of Title_m
term_frequency <- rowSums(Title_m)
# Sort term_frequency in decreasing order
term_frequency <- sort(term_frequency,decreasing=TRUE)
# View the top 10 most common words
term_frequency[1:15]

##        mind         map    learning     mapping   education    research 
##          96          59          29          29          12          11 
##    teaching application   knowledge    thinking        tool    analysis 
##          11           8           8           8           8           7 
##     concept        maps    strategy 
##           7           7           7

# Plot a barchart of the 10 most common words
barplot(term_frequency[1:15], col = "tan", las = 2)

# Vector of terms
terms_vec <- names(term_frequency)
# Create a word cloud for the values in word_freqs
wordcloud(terms_vec,term_frequency,max.words=80,rot.per = 0.35,random.order = FALSE, colors=brewer.pal(8,"Dark2"))

What’s the common terms for the target articles? (Only Abstract)

# Make a vector source from Abstract
Abstract_source <- VectorSource(MM_Data$Abstract)
# Make a volatile corpus from Abstract_source
Abstract_corpus <- VCorpus(Abstract_source)
# Clean the corpus
clean_Abstract <- clean_corpus(Abstract_corpus)
# Create a term-document matrix from the corpus
Abstract_tdm <- TermDocumentMatrix(clean_Abstract)
# Convert Abstract_tdm to a matrix
Abstract_m <- as.matrix(Abstract_tdm)
# Calculate the row sums of Abstract_m
term_frequency <- rowSums(Abstract_m)
# Sort term_frequency in decreasing order
term_frequency <- sort(term_frequency,decreasing=TRUE)
# View the top 15 most common words
term_frequency[1:15]

##        mind    learning     mapping        maps         map   knowledge 
##         403         198         147         139         135          91 
##    research information       group    thinking    teaching   technique 
##          85          76          72          71          63          61 
##    analysis      skills      groups 
##          50          50          44

# Plot a barchart of the 10 most common words
x1 <- barplot(term_frequency[1:15], col = "tan", las = 2,main="Top 15 Most Frequent Terms")
y1 <- as.matrix(term_frequency[1:15])
gg <- text(x1,y1+2,labes=as.character(y1))

## Warning in text.default(x1, y1 + 2, labes = as.character(y1)): "labes" is not a
## graphical parameter

# Vector of terms
terms_vec <- names(term_frequency)
# Create a word cloud for the values in word_freqs
wordcloud(terms_vec,term_frequency,max.words=80,rot.per = 0.35,random.order = FALSE, colors=brewer.pal(8,"Dark2"))

wordcloud(terms_vec,term_frequency,max.words=80,rot.per = 0.35,random.order = FALSE)

Section 4 The contents of the Mind Map Studies

Subjects & Target

table(MM_Data$Subject)

## 
##              Arts           Biology          Business  Computer Science 
##                 1                 2                 3                17 
##        e-learning         Economics         Education       Engineering 
##                 6                 3                16                 4 
##           General Language Learning         Marketing           Medical 
##                13                11                 2                20 
##          Physical           Science    Social Science Teacher Education 
##                 4                 2                 2                 1 
##           Writing 
##                 6

table(MM_Data$Target)

## 
##       Concept Design Cooperative Learning   Creatical Thinking 
##                    1                    3                    1 
##    Creative Thinking              General   Improving Learning 
##                    7                   42                   46 
##   Improving Teaching      Problem Solving          Researching 
##                    1                    1                   11

Mind Map Research Characteristics

Mind Map Usage

table(MM_Data$`MindMap Usage`)

## 
##         Both Hand Written   Not Report     Software 
##            4           32           18           59

Mind Map Duration

table(MM_Data$`MindMap Duration`)

## 
##   Long Term Median Term  Not Report  Short term 
##           9           8          42          54

Mind Map Calling

table(MM_Data$`Primary-Calling`)

## 
## Interchangeably        Mind Map    Mind Mapping          Others 
##              53              50               6               4

Research Settings

Quantitative or Qualitative

table(MM_Data$`quali or quant`)

## 
## Mixed-Method  Qualitative Quantitative 
##            5           55           53

Research Design

table(MM_Data$`Research Design`)

## 
##                    Case Study                 Correlational 
##                             1                             2 
##                   Descriptive                Embeded Design 
##                            20                             1 
##                  Experimental Explanatory Sequential Design 
##                             8                             2 
## Exploratory Sequential Design                   Focus group 
##                             2                            14 
##               Grounded Theory             Literature Review 
##                            11                             4 
##                 Meta-Analysis                     Narrative 
##                             1                            25 
##            Quasi-experimental 
##                            22

Quality of Evidence

table(MM_Data$`Quality of the Evidence`)

## 
##               LV1-Meta                LV2-RCT                 LV3-CT 
##                      1                     12                     24 
##         LV4-Case_Study        LV5-Descriptive LV6-Single_Qualitative 
##                     18                     28                     30

Section 5 Thematic Analysis

Hand vs. Software

## Pooling out the all Mind Map paper used software
MM_software <- MM_Data[which(MM_Data$`MindMap Usage` =="Software"),]
## Pooling out all the abstracts from software paper
All_software <- paste(MM_software$Abstract,collapse = "")
## Pooling out all the Mind Map paper used hand written
MM_hand <- MM_Data[which(MM_Data$`MindMap Usage`=="Hand Written"),]
## Pooling out all the abstracts from hand-made MM paper
All_hand <- paste(MM_hand$Abstract,collapse = "")
All_papers <- c(All_software,All_hand)
## Clean all papers
All_papers <- VectorSource(All_papers)
All_corpus <- VCorpus(All_papers)
All_clean <- clean_corpus(All_corpus)
All_tdm <- TermDocumentMatrix(All_clean)
colnames(All_tdm) <- c("Mind Map Use Software","Mind Map by hand")
All_m <- as.matrix(All_tdm)

### ### What are the difference between Methodology paper and Apply paper in their dissimilar terms? (Comparison Cloud)
# Make comparison cloud
comparison.cloud(All_m,max.words=30,random.order = FALSE,rot.per=0.35,colors=brewer.pal(max(3,ncol(All_m)),"Dark2"))

### What are the difference between software paper and hand written paper in their common terms? (pyramid plot)
## Identify terms shared by both documents
common_words <- subset(All_m,All_m[,1]>0 & All_m[,2]>0)
## Find most commonly shared words
difference <- abs(common_words[,1]-common_words[,2])
common_words <- cbind(common_words,difference)
common_words <- common_words[order(common_words[,3],decreasing = TRUE),]
top25_df <- data.frame(x=common_words[1:25],1,y=common_words[1:25,2],labels=rownames(common_words[1:25,]))
top25_df <- top25_df[order(top25_df$labels,decreasing=TRUE),]
## Make pyramid plot
pyramid.plot(top25_df$x,top25_df$y,labels =top25_df$labels,main="Words in Common",gap=80,raxlab=NULL,unit=NULL,top.labels=c("Mind Map by software","word","Mind Map by hand"))

## 199 199

## [1] 5.1 4.1 4.1 2.1

Short_Term vs. Medium & Long_Term

## Pooling out the all short term Mind Map intervention
MM_short <- MM_Data[which(MM_Data$`MindMap Duration` =="Short term"),]
## Pooling out all the abstracts from short term Mind Map intervention
All_short <- paste(MM_short$Abstract,collapse = "")
## Pooling out all the Mind Median and Long term Mind Map Intervention
MM_Median<- MM_Data[which(MM_Data$`MindMap Duration`=="Median Term"),]
MM_long <- MM_Data[which(MM_Data$`MindMap Duration`=="Long Term"),]
MM_MedianNlong <- rbind(MM_Median,MM_long)
## Pooling out all the abstracts from hand-made MM paper
All_MedianNlong <- paste(MM_MedianNlong$Abstract,collapse = "")
All_papers <- c(All_short,All_MedianNlong)
## Clean all papers
All_papers <- VectorSource(All_papers)
All_corpus <- VCorpus(All_papers)
All_clean <- clean_corpus(All_corpus)
All_tdm <- TermDocumentMatrix(All_clean)
colnames(All_tdm) <- c("Short Term Intervention","Medium & Long Term Intervention")
All_m <- as.matrix(All_tdm)

### ### What are the difference between Methodology paper and Apply paper in their dissimilar terms? (Comparison Cloud)
# Make comparison cloud
comparison.cloud(All_m,max.words=30,random.order = FALSE,rot.per=0.35,colors=brewer.pal(max(3,ncol(All_m)),"Dark2"))

## Warning in comparison.cloud(All_m, max.words = 30, random.order = FALSE, :
## metacognitive could not be fit on page. It will not be plotted.

## Warning in comparison.cloud(All_m, max.words = 30, random.order = FALSE, :
## traditional could not be fit on page. It will not be plotted.

## Warning in comparison.cloud(All_m, max.words = 30, random.order = FALSE, :
## significant could not be fit on page. It will not be plotted.

## Warning in comparison.cloud(All_m, max.words = 30, random.order = FALSE, :
## anatomy could not be fit on page. It will not be plotted.

## Warning in comparison.cloud(All_m, max.words = 30, random.order = FALSE, :
## research could not be fit on page. It will not be plotted.

## Warning in comparison.cloud(All_m, max.words = 30, random.order = FALSE, :
## cooperative could not be fit on page. It will not be plotted.

## Warning in comparison.cloud(All_m, max.words = 30, random.order = FALSE, :
## higher could not be fit on page. It will not be plotted.

## Warning in comparison.cloud(All_m, max.words = 30, random.order = FALSE, : mean
## could not be fit on page. It will not be plotted.

### What are the difference between software paper and hand written paper in their common terms? (pyramid plot)
## Identify terms shared by both documents
common_words <- subset(All_m,All_m[,1]>0 & All_m[,2]>0)
## Find most commonly shared words
difference <- abs(common_words[,1]-common_words[,2])
common_words <- cbind(common_words,difference)
common_words <- common_words[order(common_words[,3],decreasing = TRUE),]
top25_df <- data.frame(x=common_words[1:25],1,y=common_words[1:25,2],labels=rownames(common_words[1:25,]))
top25_df <- top25_df[order(top25_df$labels,decreasing=TRUE),]
## Make pyramid plot
pyramid.plot(top25_df$x,top25_df$y*3,labels =top25_df$labels,main="Words in Common",gap=80,raxlab=NULL,unit=NULL,top.labels=c("Short Term Intervention","word","Medium & Long Term Intervention"))

## 198 198

## [1] 5.1 4.1 4.1 2.1

Qualitative vs. Quantitative

## Pooling out the all Qualitative Mind Map Paper
MM_Quali <- MM_Data[which(MM_Data$`quali or quant` =="Qualitative"),]
## Pooling out all the Qualitative Mind Map Paper
All_Quali <- paste(MM_Quali$Abstract,collapse = "")
## Pooling out all the Quantitative Mind Map Paper
MM_Quant <- MM_Data[which(MM_Data$`quali or quant`=="Quantitative"),]
## Pooling out all the Quantitative Mind Map Paper
All_Quant <- paste(MM_Quant$Abstract,collapse = "")
All_papers <- c(All_Quali,All_Quant)
## Clean all papers
All_papers <- VectorSource(All_papers)
All_corpus <- VCorpus(All_papers)
All_clean <- clean_corpus(All_corpus)
All_tdm <- TermDocumentMatrix(All_clean)
colnames(All_tdm) <- c("Qualitative paper","Quantitative paper")
All_m <- as.matrix(All_tdm)

### ### What are the difference between Methodology paper and Apply paper in their dissimilar terms? (Comparison Cloud)
# Make comparison cloud
comparison.cloud(All_m,max.words=30,random.order = FALSE,rot.per=0.35,colors=brewer.pal(max(3,ncol(All_m)),"Dark2"))

## Warning in comparison.cloud(All_m, max.words = 30, random.order = FALSE, :
## qualitative could not be fit on page. It will not be plotted.

### What are the difference between software paper and hand written paper in their common terms? (pyramid plot)
## Identify terms shared by both documents
common_words <- subset(All_m,All_m[,1]>0 & All_m[,2]>0)
## Find most commonly shared words
difference <- abs(common_words[,1]-common_words[,2])
common_words <- cbind(common_words,difference)
common_words <- common_words[order(common_words[,3],decreasing = TRUE),]
top25_df <- data.frame(x=common_words[1:25],1,y=common_words[1:25,2],labels=rownames(common_words[1:25,]))
top25_df <- top25_df[order(top25_df$labels,decreasing=TRUE),]
## Make pyramid plot
pyramid.plot(top25_df$x,top25_df$y,labels =top25_df$labels,main="Words in Common",gap=80,raxlab=NULL,unit=NULL,top.labels=c("Qualitative Paper","word","Quantitative Paper"))

## 210 210

## [1] 5.1 4.1 4.1 2.1

Section 6 Cross Category comparison

Quali or Quant vs. Mind Map Usage

# Pool the data
Q1 <- MM_Data[,c(11,14)]
colnames(Q1) <- c("Usage","QUA")
Q1_soft <- subset(Q1,Usage=="Software")
table(Q1_soft$QUA)/59

## 
## Mixed-Method  Qualitative Quantitative 
##   0.03389831   0.62711864   0.33898305

Q1_hand <- subset(Q1,Usage=="Hand Written")
table(Q1_hand$QUA)/32

## 
## Mixed-Method  Qualitative Quantitative 
##      0.09375      0.18750      0.71875

Mind Map Duration vs. Mind Map Usage

# Pool the data
Q2 <- MM_Data[,c(11,12)]
colnames(Q2) <- c("Usage","Duration")
Q2_soft <- subset(Q2,Usage=="Software")
table(Q2_soft$Duration)/59

## 
##   Long Term Median Term  Not Report  Short term 
##  0.05084746  0.06779661  0.44067797  0.44067797

Q2_hand <- subset(Q2,Usage=="Hand Written")
table(Q2_hand$Duration)/32

## 
##   Long Term Median Term  Not Report  Short term 
##     0.18750     0.09375     0.03125     0.68750

Mind Map decades vs. Mind Map Usage

# Pool the data 
Q3 <- MM_Data[,c(7,11)]
Q3_first <- subset(Q3,Year<=2009)
Q3_Second <- subset(Q3,Year>2009)
table(Q3_first$`MindMap Usage`)/30

## 
##         Both Hand Written   Not Report     Software 
##   0.06666667   0.30000000   0.10000000   0.53333333

table(Q3_Second$`MindMap Usage`)/83

## 
##         Both Hand Written   Not Report     Software 
##   0.02409639   0.27710843   0.18072289   0.51807229

Mind Map decades vs. Mind Map Duration

# Pool the data 
Q4 <- MM_Data[,c(7,12)]
Q4_first <- subset(Q4,Year<=2009)
Q4_Second <- subset(Q4,Year>2009)
table(Q4_first$`MindMap Duration`)/30

## 
## Median Term  Not Report  Short term 
##         0.1         0.4         0.5

table(Q4_Second$`MindMap Duration`)/83

## 
##   Long Term Median Term  Not Report  Short term 
##  0.10843373  0.06024096  0.36144578  0.46987952

Mind Map decades vs. Mind Map Research Type

# Pool the data 
Q5 <- MM_Data[,c(7,14)]
Q5_first <- subset(Q5,Year<=2009)
Q5_Second <- subset(Q5,Year>2009)
table(Q5_first$`quali or quant`)/30

## 
##  Qualitative Quantitative 
##    0.5666667    0.4333333

table(Q5_Second$`quali or quant`)/83

## 
## Mixed-Method  Qualitative Quantitative 
##   0.06024096   0.45783133   0.48192771

MM_data

Cheng Hua

2022-07-30

Cheng’s Dissertation

Qualitative EQTA

Session 1: Prepare for the analysis

Load the dataset

Session 2: Descriptive Data Analysis on Basic Paper Information

Article Numbers by Years

Most Popular Mind Map Author

Mind Map by Author Numbers

Mind Map Studies by Country

Session 3: WordCoulds for making the categories

Preparing the data cleaning

Dealing with more stop words and duplicate words

What’s the common terms for the target articles? (Only Title)

What’s the common terms for the target articles? (Only Abstract)

Section 4 The contents of the Mind Map Studies

Subjects & Target

Mind Map Research Characteristics

Research Settings

Section 5 Thematic Analysis

Hand vs. Software

Short_Term vs. Medium & Long_Term

Qualitative vs. Quantitative

Section 6 Cross Category comparison

Quali or Quant vs. Mind Map Usage

Mind Map Duration vs. Mind Map Usage

Mind Map decades vs. Mind Map Usage

Mind Map decades vs. Mind Map Duration

Mind Map decades vs. Mind Map Research Type