How to remove all unspecified specified words from dataframe column in R

Here is a way with base gregexpr and regmatches.

pattern <- paste0("\\<", termstokeep, "\\>")
pattern <- paste(pattern, collapse = "|")
m <- gregexpr(pattern, df1$bio)
r <- regmatches(df1$bio, m)

df1$bio_clean <- sapply(r, paste, collapse = " ")

^{Created on 2022-02-22 by the reprex package (v2.0.1)}

Data

termstokeep <-
c("love", "life", "follow", "live", "just", "like", "music", 
  "regist", "trademark", "make", "fan", "one", "copyright", "lover", 
  "thing", "world", "time", "god", "can", "get", "design", "peopl", 
  "artist", "girl", "univers", "writer", "will", "student", "work", 
  "busi", "good", "new", "know", "friend", "famili", "best", "day", 
  "account", "market", "sport", "art", "game", "manag", "want", 
  "book", "enthusiast", "person", "alway", "travel", "never", "free", 
  "real", "help", "dream", "servic", "mom", "husband", "profession", 
  "beauti", "offici", "wife", "now", "news", "social", "food", 
  "come", "father", "heart", "educ", "develop", "need", "anim", 
  "everyth", "proud", "tri", "year", "happi", "also", "media", 
  "way", "man", "team", "produc", "look", "state", "take", "back", 
  "support", "director", "home", "find", "call", "engin", "learn", 
  "provid", "photograph", "great", "author", "video", "guy", "communiti", 
  "coach", "name", "big", "passion", "see", "teacher", "school", 
  "product", "sinc", "gamer", "enjoy", "keep", "player", "better", 
  "let", "believ", "mother", "think", "mind", "dog", "futur", "give", 
  "colleg", "say", "owner", "jesus", "fun", "got", "littl", "chang", 
  "founder", "boy", "use", "first", "liberal", "write", "footbal", 
  "kid", "fuck", "event", "polit", "consult", "care", "conserv", 
  "much", "health", "technolog", "tech", "opinion", "stay", "everi", 
  "right", "full", "former", "member", "special", "well", "young", 
  "high", "creat", "snap", "entrepreneur", "movi", "feel", "view", 
  "compani", "coffe", "cat", "citi", "human", "digit", "show", 
  "singer", "sometim", "interest", "dad", "watch", "scienc", "creativ", 
  "blogger", "base", "addict", "fit", "read", "bless", "fashion", 
  "part", "noth", "run", "forev", "editor", "born", "hard", "die", 
  "around", "onlin", "nerd", "class", "web", "musician", "made", 
  "stuff", "leader", "ever", "inspir", "still", "christian", "place", 
  "current", "public", "danc", "pleas", "geek", "talk", "film", 
  "realli", "babi", "someth", "page", "rock", "lot", "women", "lead", 
  "two")


df1 <- read.table(text = "
account     bio
38374   'i love candy as much as life itself proud liberal'
45673   'can all just get along'
94928   'conserv christian mom and proud pro trump veteran maga'
11204   'professor of women and gender studies at wesleyan university blacklivesmatter'
37465   'former ohio state football coach now a proud papa to seven grandchildren'
", header = TRUE)

^{Created on 2022-02-22 by the reprex package (v2.0.1)}

A possible solution, based on tidyverse:

library(tidyverse)

df %>% 
  rowwise %>% 
  mutate(bio = str_split(bio, "\\s") %>% unlist %>% intersect(words) %>%
    str_c(collapse = " ")) %>% 
  ungroup

#> # A tibble: 5 x 2
#>   account bio                         
#>     <int> <chr>                       
#> 1   38374 love much life proud liberal
#> 2   45673 can just get                
#> 3   94928 conserv christian mom proud 
#> 4   11204 women                       
#> 5   37465 former state coach now proud

Here is another base R option:

df$bio <- sapply(lapply(strsplit(df$bio, "\\s"), intersect, termstokeep),
       paste, collapse = " ")

Output

  account                          bio
1   38374 love much life proud liberal
2   45673                 can just get
3   94928  conserv christian mom proud
4   11204                        women
5   37465 former state coach now proud

Data (thanks @RuiBarradas!)

df <- structure(list(account = c(38374L, 45673L, 94928L, 11204L, 37465L
), bio = c("i love candy as much as life itself proud liberal", 
"can all just get along", "conserv christian mom and proud pro trump veteran maga", 
"professor of women and gender studies at wesleyan university blacklivesmatter", 
"former ohio state football coach now a proud papa to seven grandchildren"
)), class = "data.frame", row.names = c(NA, -5L))

termstokeep <- c("love", "life", "follow", "live", "just", "like", "music", 
"regist", "trademark", "make", "fan", "one", "copyright", "lover", 
"thing", "world", "time", "god", "can", "get", "design", "peopl", 
"artist", "girl", "univers", "writer", "will", "student", "work", 
"busi", "good", "new", "know", "friend", "famili", "best", "day", 
"account", "market", "sport", "art", "game", "manag", "want", 
"book", "enthusiast", "person", "alway", "travel", "never", "free", 
"real", "help", "dream", "servic", "mom", "husband", "profession", 
"beauti", "offici", "wife", "now", "news", "social", "food", 
"come", "father", "heart", "educ", "develop", "need", "anim", 
"everyth", "proud", "tri", "year", "happi", "also", "media", 
"way", "man", "team", "produc", "look", "state", "take", "back", 
"support", "director", "home", "find", "call", "engin", "learn", 
"provid", "photograph", "great", "author", "video", "guy", "communiti", 
"coach", "name", "big", "passion", "see", "teacher", "school", 
"product", "sinc", "gamer", "enjoy", "keep", "player", "better", 
"let", "believ", "mother", "think", "mind", "dog", "futur", "give", 
"colleg", "say", "owner", "jesus", "fun", "got", "littl", "chang", 
"founder", "boy", "use", "first", "liberal", "write", "footbal", 
"kid", "fuck", "event", "polit", "consult", "care", "conserv", 
"much", "health", "technolog", "tech", "opinion", "stay", "everi", 
"right", "full", "former", "member", "special", "well", "young", 
"high", "creat", "snap", "entrepreneur", "movi", "feel", "view", 
"compani", "coffe", "cat", "citi", "human", "digit", "show", 
"singer", "sometim", "interest", "dad", "watch", "scienc", "creativ", 
"blogger", "base", "addict", "fit", "read", "bless", "fashion", 
"part", "noth", "run", "forev", "editor", "born", "hard", "die", 
"around", "onlin", "nerd", "class", "web", "musician", "made", 
"stuff", "leader", "ever", "inspir", "still", "christian", "place", 
"current", "public", "danc", "pleas", "geek", "talk", "film", 
"realli", "babi", "someth", "page", "rock", "lot", "women", "lead", 
"two")