Academic Article Organizer and Analyzer.Rmd

---
title: "Academic Article Organizer and Analyzer"
author: "Your Name"
date: "2023-01-04"
output: html_document
---

```{r setup, include=FALSE}
# Clearing the workspace and setting global chunk options
rm(list=ls())
knitr::opts_chunk$set(echo = TRUE)
```

```{r Load all packages}
# Loading necessary libraries
library(RPostgreSQL)
library(dplyr)
library(dbplyr)
library(data.table)
library(lubridate)
library(reshape2)
library(stringr)
library(tidyverse)
library(readxl)
library(knitr)
library(ggplot2)
library(udpipe)
```

```{r Get a list of existing articles in PDF format}
# Define the base path for articles
base_path <- "path/to/your/articles/directory"

# Listing PDF files in a specific directory
file_list <- as.data.frame(list.files(file.path(base_path, "Deep Learning-Based Recommendation System Systematic Review and Classification"), 
                                      all.files = TRUE, 
                                      full.names = FALSE))
colnames(file_list) <- c("article_title")

# Listing PDF files in the article classification directory
article_list <- as.data.frame(list.files(file.path(base_path, "Article Classification"), 
                                         pattern = ".pdf$", 
                                         full.names = TRUE, 
                                         recursive = TRUE, 
                                         include.dirs = TRUE))

# Getting a list of reviewed articles
old_names <- as.data.frame(list.files(file.path(base_path, "Reviewed Articles/Thesis"), 
                                      all.files = TRUE, 
                                      full.names = FALSE))
colnames(old_names) <- c("article_title")

# Cleaning the file names and removing unwanted characters
old_names <- old_names %>% 
  filter(!article_title %in% c(".", "..", ".DS_Store"))

new_names <- old_names
new_names$article_title <- gsub("[[:punct:]]", " ", new_names$article_title)
new_names$article_title <- gsub("[[:digit:]]+", " ", new_names$article_title)
new_names$article_title <- lapply(new_names$article_title, tolower)
new_names$article_title <- trimws(new_names$article_title)
new_names$article_title <- gsub("\\s+", " ", new_names$article_title)
new_names$article_title <- gsub(" +"," ",new_names$article_title) 
new_names$article_title<- str_to_title(new_names$article_title)
new_names$article_title <- gsub("E Commerce","eCommerce",new_names$article_title) 
new_names$article_title <- gsub(" Pdf","",new_names$article_title) 
new_names <- new_names
new_names <- paste0(new_names$article_title, '.pdf')

# Renaming the files in the specified directory
old.names <- (old_names$article_title)
thesis_path <- file.path(base_path, "Reviewed Articles/Thesis")
file.rename(from = paste0(thesis_path, old.names), to = paste0(thesis_path, new_names))
```

```{r Rename the pre-processing files}
# Renaming files in the pre-processing directory
preprocess_path <- file.path(base_path, "pre-processing/round 2")

old_names <- as.data.frame(list.files(preprocess_path, full.names = FALSE))
colnames(old_names) <- c("article_title")

# Cleaning and modifying file names
new_names <- old_names
new_names$article_title  <- gsub("_.*","",new_names$article_title)
new_names$article_title <- gsub("[[:punct:]]", " ", new_names$article_title)
new_names$article_title <- gsub("[[:digit:]]+", " ", new_names$article_title)
new_names$article_title <- lapply(new_names$article_title, tolower)
new_names$article_title <- trimws(new_names$article_title)
new_names$article_title <- gsub("\\s+", " ", new_names$article_title)
new_names$article_title <- gsub(" +"," ",new_names$article_title) 
new_names$article_title <- gsub(" pdf", "", new_names$article_title)
new_names$article_title<- str_to_sentence(new_names$article_title)
new_names$article_title <- gsub("e commerce|ecommerce","e-commerce",new_names$article_title) 
new_names$article_title <- gsub("E commerce|Ecommerce","E-commerce",new_names$article_title) 
new_names <- new_names
new_names <- paste0(new_names$article_title, '.pdf')
old.names <- (old_names$article_title)

# Renaming files
file.rename(from = paste0(preprocess_path, old.names), to = paste0(preprocess

_path, new_names))
```

```{r Mendeley citation analysis}
# Loading and processing citation data
library(bib2df)

citation_path <- "path/to/your/citation/file"
thesis_articles <- as_tibble(bib2df(citation_path))
thesis_articles <- thesis_articles %>% 
  select(CATEGORY, BIBTEXKEY, AUTHOR, JOURNAL, PUBLISHER, TITLE, VOLUME, YEAR, ABSTRACT, DOI, ISSN, KEYWORDS, URL, ISBN)

# Processing abstracts for citation analysis
abstract <- thesis_articles %>% select(TITLE, BIBTEXKEY, ABSTRACT)
colnames(abstract) <- c("title", "bibtexkey", "abstract")
abstract <- data.frame(tibble::rownames_to_column(abstract, "doc_id"), stringsAsFactors=FALSE)
abstract_f <- unnest_sentences_(abstract, "sents", "abstract")

# Cleaning and formatting abstract sentences
abstract_f$sents <- trimws(abstract_f$sents)
abstract_f[is.na(abstract_f)] <- ""
abstract_f$sents <- str_to_sentence(abstract_f$sents)
abstract_f$title <- str_to_title(abstract_f$title)

# Cleaning and formatting the main thesis articles data
thesis_articles <- as.data.frame(lapply(thesis_articles, as.character), stringsAsFactors=FALSE)
thesis_articles$AUTHOR <- gsub("c()", "", thesis_articles$AUTHOR)
thesis_articles$TITLE <- str_to_title(thesis_articles$TITLE)
thesis_articles$ABSTRACT <- str_to_sentence(thesis_articles$ABSTRACT)
thesis_articles$KEYWORDS <- trimws(tolower(thesis_articles$KEYWORDS))

# Writing the processed data to Excel files
output_path <- "path/to/your/output/directory"
write.xlsx(abstract_f, file.path(output_path, "thesis_article_analysis_v4.xlsx"), 
           sheetName="abstract_sentence_classification", append=TRUE, row.names=FALSE)
write.xlsx(thesis_articles, file.path(output_path, "thesis_article_analysis_v4.xlsx"), 
           sheetName="thesis_articles", append=TRUE, row.names=FALSE)
```