##
## 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
library(ggplot2)
library(ggraph)
library(igraph)
##
## Attaching package: 'igraph'
## The following objects are masked from 'package:dplyr':
##
## as_data_frame, groups, union
## The following objects are masked from 'package:stats':
##
## decompose, spectrum
## The following object is masked from 'package:base':
##
## union
library(readr)
library(litsearchr)
setwd("C:/Users/subas/OneDrive - Texas A&M Transportation Institute/0_PAPERS/ALL_PAPERS/Journal/Submitted/2020_2021/SYSTEMATIC_LIT/litsearchR")
naive_results <- import_results(file="BikeShare.ris")
## Reading file BikeShare.ris ... done
## [1] 103
#naive_results
colnames(naive_results)
## [1] "document_type" "source_type" "author" "year"
## [5] "title" "journal" "volume" "abstract"
## [9] "keywords" "doi" "accession_zr" "url"
## [13] "publisher" "start_page" "issue" "eppi_id"
## [17] "ET" "issn"
#naive_results[1, "title"]
#naive_results[1, "keywords"]
extract_terms(keywords=naive_results[, "keywords"], method="tagged")
## Loading required namespace: stopwords
## [1] "activity centers"
## [2] "after studies"
## [3] "american community survey"
## [4] "annual average daily traffic"
## [5] "arlington county virginia"
## [6] "baltimore maryland"
## [7] "bayes' theorem"
## [8] "bicycle commuting"
## [9] "bicycle facilities"
## [10] "bicycle helmets"
## [11] "bicycle lanes"
## [12] "bicycle sharing"
## [13] "bicycle sharing stations"
## [14] "bicycle travel"
## [15] "binomial distributions"
## [16] "birmingham alabama"
## [17] "boston massachusetts"
## [18] "built environment"
## [19] "capital bikeshare"
## [20] "case studies"
## [21] "chicago illinois"
## [22] "choice models"
## [23] "citi bike"
## [24] "cluster analysis"
## [25] "consumer preferences"
## [26] "crash analysis"
## [27] "data analysis"
## [28] "data mining"
## [29] "district department of transportation"
## [30] "economic benefits"
## [31] "electric vehicles"
## [32] "equity justice"
## [33] "feasibility analysis"
## [34] "feeder services"
## [35] "geographic information systems"
## [36] "global positioning system"
## [37] "helmet use"
## [38] "highway safety"
## [39] "honolulu hawaii"
## [40] "intermodal transfer"
## [41] "international comparison"
## [42] "land use"
## [43] "linear regression analysis"
## [44] "literature reviews"
## [45] "low income groups"
## [46] "mathematical models"
## [47] "membership organizations"
## [48] "metrorail washington metropolitan area"
## [49] "minneapolis minnesota"
## [50] "mobile applications"
## [51] "modal shift"
## [52] "modal split"
## [53] "mode choice"
## [54] "multimodal transportation"
## [55] "nanjing china"
## [56] "new york new york"
## [57] "nice ride"
## [58] "nonmotorized transportation"
## [59] "north america"
## [60] "online survey"
## [61] "periods of the day"
## [62] "philadelphia pennsylvania"
## [63] "population density"
## [64] "public transit"
## [65] "rail transit"
## [66] "rail transit stations"
## [67] "rapid transit"
## [68] "regression analysis"
## [69] "revealed preferences"
## [70] "route choice"
## [71] "san francisco bay area"
## [72] "san francisco california"
## [73] "service disruption"
## [74] "shared mobility"
## [75] "smart cards"
## [76] "social factors"
## [77] "socioeconomic factors"
## [78] "spatial analysis"
## [79] "spatiotemporal analysis"
## [80] "statistical analysis"
## [81] "strategic planning"
## [82] "sustainable transportation"
## [83] "time duration"
## [84] "traffic flow"
## [85] "transit riders"
## [86] "transportation planning"
## [87] "travel behavior"
## [88] "travel demand"
## [89] "travel patterns"
## [90] "travel surveys"
## [91] "trip chaining"
## [92] "trip generation"
## [93] "trip length"
## [94] "trip purpose"
## [95] "united states"
## [96] "urban areas"
## [97] "vehicle sharing"
## [98] "washington district of columbia"
## [99] "washington metropolitan area"
## [100] "weather conditions"
keywords <- extract_terms(keywords=naive_results[, "keywords"], method="tagged", min_n=1)
keywords
## [1] "access"
## [2] "accessibility"
## [3] "activity centers"
## [4] "after studies"
## [5] "age"
## [6] "american community survey"
## [7] "annual average daily traffic"
## [8] "arlington county virginia"
## [9] "attitudes"
## [10] "baltimore maryland"
## [11] "bayes' theorem"
## [12] "before"
## [13] "behavior"
## [14] "bicycle commuting"
## [15] "bicycle facilities"
## [16] "bicycle helmets"
## [17] "bicycle lanes"
## [18] "bicycle sharing"
## [19] "bicycle sharing stations"
## [20] "bicycle travel"
## [21] "bicycles"
## [22] "bicycling"
## [23] "binomial distributions"
## [24] "birmingham alabama"
## [25] "boston massachusetts"
## [26] "built environment"
## [27] "capital bikeshare"
## [28] "case studies"
## [29] "chicago illinois"
## [30] "china"
## [31] "choice models"
## [32] "citi bike"
## [33] "citibike"
## [34] "cities"
## [35] "cluster analysis"
## [36] "communities"
## [37] "commuters"
## [38] "consumer preferences"
## [39] "covid-19"
## [40] "crash analysis"
## [41] "cyclists"
## [42] "data analysis"
## [43] "data mining"
## [44] "demand"
## [45] "demographics"
## [46] "destination"
## [47] "district department of transportation"
## [48] "economic benefits"
## [49] "electric vehicles"
## [50] "equity justice"
## [51] "feasibility analysis"
## [52] "feeder services"
## [53] "gender"
## [54] "geographic information systems"
## [55] "global positioning system"
## [56] "helmet use"
## [57] "highway safety"
## [58] "honolulu hawaii"
## [59] "impacts"
## [60] "implementation"
## [61] "infrastructure"
## [62] "intermodal transfer"
## [63] "international comparison"
## [64] "jobs"
## [65] "land use"
## [66] "linear regression analysis"
## [67] "literature reviews"
## [68] "location"
## [69] "logits"
## [70] "low income groups"
## [71] "marketing"
## [72] "mathematical models"
## [73] "membership organizations"
## [74] "methodology"
## [75] "metrorail washington metropolitan area"
## [76] "minneapolis minnesota"
## [77] "mobile applications"
## [78] "mobility"
## [79] "modal shift"
## [80] "modal split"
## [81] "mode choice"
## [82] "multimodal transportation"
## [83] "nanjing china"
## [84] "new york new york"
## [85] "nice ride"
## [86] "nonmotorized transportation"
## [87] "north america"
## [88] "online survey"
## [89] "operations"
## [90] "origin"
## [91] "periods of the day"
## [92] "philadelphia pennsylvania"
## [93] "policy"
## [94] "population density"
## [95] "pricing"
## [96] "public transit"
## [97] "race"
## [98] "rail transit"
## [99] "rail transit stations"
## [100] "rapid transit"
## [101] "regression analysis"
## [102] "revealed preferences"
## [103] "revenues"
## [104] "ridership"
## [105] "route choice"
## [106] "safety"
## [107] "san francisco bay area"
## [108] "san francisco california"
## [109] "scooters"
## [110] "service disruption"
## [111] "shared mobility"
## [112] "smart cards"
## [113] "social factors"
## [114] "socioeconomic factors"
## [115] "spatial analysis"
## [116] "spatiotemporal analysis"
## [117] "statistical analysis"
## [118] "strategic planning"
## [119] "suburbs"
## [120] "surveys"
## [121] "sustainable transportation"
## [122] "time duration"
## [123] "tourism"
## [124] "tourists"
## [125] "traffic flow"
## [126] "transfers"
## [127] "transit riders"
## [128] "transportation planning"
## [129] "travel behavior"
## [130] "travel demand"
## [131] "travel patterns"
## [132] "travel surveys"
## [133] "trip chaining"
## [134] "trip generation"
## [135] "trip length"
## [136] "trip purpose"
## [137] "united states"
## [138] "urban areas"
## [139] "validation"
## [140] "vehicle sharing"
## [141] "washington district of columbia"
## [142] "washington metropolitan area"
## [143] "weather conditions"
extract_terms(text=naive_results[, "title"], method="fakerake", min_freq=3, min_n=2)
## [1] "bikeshare access" "bikeshare demand"
## [3] "bikeshare programs" "bikeshare ridership"
## [5] "bikeshare station" "bikeshare system"
## [7] "bikeshare systems" "bikeshare trips"
## [9] "bikeshare users" "capital bikeshare"
## [11] "capital bikeshare trips" "casual users"
## [13] "disadvantaged communities" "dockless bikeshare"
## [15] "route choice"
clinpsy_stopwords <- read_lines("stop.txt")
#clinpsy_stopwords
all_stopwords <- c(get_stopwords("English"), clinpsy_stopwords)
title_terms <- extract_terms(
text=naive_results[, "title"],
method="fakerake",
min_freq=3, min_n=2,
stopwords=all_stopwords
)
title_terms
## [1] "bikeshare access" "bikeshare demand"
## [3] "bikeshare programs" "bikeshare ridership"
## [5] "bikeshare station" "bikeshare system"
## [7] "bikeshare systems" "bikeshare trips"
## [9] "bikeshare users" "capital bikeshare"
## [11] "capital bikeshare trips" "casual users"
## [13] "disadvantaged communities" "dockless bikeshare"
## [15] "route choice"
terms <- unique(c(keywords, title_terms))
docs <- paste(naive_results[, "title"], naive_results[, "abstract"])
dfm <- create_dfm(elements=docs, features=terms)
g <- create_network(dfm, min_studies=3)
ggraph(g, layout="stress") +
coord_fixed() +
expand_limits(x=c(-3, 3)) +
geom_edge_link(aes(alpha=weight)) +
geom_node_point(shape="circle filled", fill="white") +
geom_node_text(aes(label=name), hjust="outward", check_overlap=TRUE) +
guides(edge_alpha=FALSE)+theme_bw(base_size=18)
## Warning: `guides(<scale> = FALSE)` is deprecated. Please use `guides(<scale> =
## "none")` instead.
strengths <- strength(g)
data.frame(term=names(strengths), strength=strengths, row.names=NULL) %>%
mutate(rank=rank(strength, ties.method="min")) %>%
arrange(strength) ->
term_strengths
term_strengths
## term strength rank
## 1 bikeshare access 20 1
## 2 transfers 21 2
## 3 tourism 22 3
## 4 scooters 23 4
## 5 citi bike 24 5
## 6 sustainable transportation 24 5
## 7 trip generation 24 5
## 8 weather conditions 24 5
## 9 cluster analysis 27 9
## 10 route choice 27 9
## 11 global positioning system 28 11
## 12 china 29 12
## 13 transit riders 29 12
## 14 commuters 30 14
## 15 spatial analysis 30 14
## 16 capital bikeshare trips 31 16
## 17 bicycle sharing 32 17
## 18 marketing 33 18
## 19 helmet use 35 19
## 20 trip purpose 35 19
## 21 public transit 38 21
## 22 rail transit 38 21
## 23 jobs 39 23
## 24 disadvantaged communities 39 23
## 25 implementation 43 25
## 26 before 46 26
## 27 travel patterns 49 27
## 28 surveys 51 28
## 29 methodology 52 29
## 30 mode choice 52 29
## 31 bikeshare ridership 57 31
## 32 travel behavior 60 32
## 33 north america 66 33
## 34 pricing 67 34
## 35 cyclists 69 35
## 36 dockless bikeshare 71 36
## 37 demographics 72 37
## 38 safety 75 38
## 39 urban areas 77 39
## 40 bikeshare demand 78 40
## 41 casual users 78 40
## 42 race 80 42
## 43 gender 82 43
## 44 operations 85 44
## 45 land use 90 45
## 46 united states 113 46
## 47 built environment 114 47
## 48 impacts 117 48
## 49 bicycles 119 49
## 50 destination 121 50
## 51 accessibility 122 51
## 52 bikeshare trips 125 52
## 53 origin 126 53
## 54 bicycling 135 54
## 55 communities 148 55
## 56 bikeshare programs 151 56
## 57 behavior 160 57
## 58 mobility 160 57
## 59 policy 167 59
## 60 bikeshare users 175 60
## 61 demand 179 61
## 62 capital bikeshare 182 62
## 63 bikeshare station 183 63
## 64 infrastructure 198 64
## 65 location 204 65
## 66 ridership 215 66
## 67 access 246 67
## 68 cities 304 68
## 69 bikeshare systems 341 69
## 70 bikeshare system 444 70
## 71 age 543 71
cutoff_fig <- ggplot(term_strengths, aes(x=rank, y=strength, label=term)) +
geom_line() +
geom_point() +
geom_text(data=filter(term_strengths, rank>5), hjust="right",
nudge_y=20, check_overlap=TRUE)+theme_bw(base_size=18)
cutoff_fig
cutoff_cum <- find_cutoff(g, method="cumulative", percent=0.8)
cutoff_cum
## [1] 72
cutoff_fig +
geom_hline(yintercept=cutoff_cum, linetype="dashed")
get_keywords(reduce_graph(g, cutoff_cum))
## [1] "access" "accessibility" "age"
## [4] "behavior" "bicycles" "bicycling"
## [7] "built environment" "capital bikeshare" "cities"
## [10] "communities" "demand" "demographics"
## [13] "destination" "gender" "impacts"
## [16] "infrastructure" "land use" "location"
## [19] "mobility" "operations" "origin"
## [22] "policy" "race" "ridership"
## [25] "safety" "united states" "urban areas"
## [28] "bikeshare demand" "bikeshare programs" "bikeshare station"
## [31] "bikeshare system" "bikeshare systems" "bikeshare trips"
## [34] "bikeshare users" "casual users"
cutoff_change <- find_cutoff(g, method="changepoint", knot_num=3)
cutoff_change
## [1] 90 215 304 543
cutoff_fig +
geom_hline(yintercept=cutoff_change, linetype="dashed")
g_redux <- reduce_graph(g, cutoff_change[1])
selected_terms <- get_keywords(g_redux)
selected_terms
## [1] "access" "accessibility" "age"
## [4] "behavior" "bicycles" "bicycling"
## [7] "built environment" "capital bikeshare" "cities"
## [10] "communities" "demand" "destination"
## [13] "impacts" "infrastructure" "land use"
## [16] "location" "mobility" "origin"
## [19] "policy" "ridership" "united states"
## [22] "bikeshare programs" "bikeshare station" "bikeshare system"
## [25] "bikeshare systems" "bikeshare trips" "bikeshare users"