Figure A1
A Python code snippet demonstrates keyword extraction using Key B E R T with N L T K stopwords and custom filtering.The snippet shows a Python script for extracting keywords from text data using the Key B E R T library. At the top, required libraries are imported, including: Line 1 : At indentation level 0, import n l t k. Line 2 : At indentation level 0, import pandas as p d. Line 3 : At indentation level 0, from n l t k dot corpus import stopwords. Line 4 : At indentation level 0, n l t k dot download open parenthesis single quote stopwords single quote close parenthesis. Line 5 : At indentation level 0, from keybert import Key B E R T. Line 6 : At indentation level 0, stop underscore words equals stopwords dot words open parenthesis single quote english single quote close parenthesis plus custom stopwords. Line 7 : At indentation level 0, k w model equals Key B E R T open parenthesis single quote roberta minus base single quote close parenthesis. Line 8 : At indentation level 0, texts equals d f open square bracket single quote raw text single quote close square bracket dot tolist open parenthesis close parenthesis. Line 9 : At indentation level 0, keywords equals k w underscore model dot extract underscore keywords open parenthesis texts comma keyphrase underscore ngram underscore range equals open parenthesis 1 comma 3 close parenthesis. Line 10 : At indentation level 0, comma stop underscore words equals stop underscore words comma top underscore n equals 10 close parenthesis. Line 11 : At indentation level 0, keywords underscore only equals open square bracket open square bracket k w for k w comma score in k w list close square bracket for k w underscore list in keywords close square bracket. Line 12 : At indentation level 0, scores underscore only equals open square bracket open square bracket score for k w comma score in k w list close square bracket for k w list in keywords close square bracket. Line 13 : At indentation level 0, keywords underscore only equals p d dot DataFrame open parenthesis keywords underscore only close parenthesis. Line 14 : At indentation level 0, scores underscore only equals p d dot DataFrame open parenthesis scores underscore only close parenthesis. Line 15 : At indentation level 0, keywords separated equals p d dot concat open parenthesis open square bracket keywords underscore only comma scores underscore only close square bracket comma axis equals 1 close parenthesis. Below the code, a long list of default N L T K English stopwords is displayed, including common words such as: N L T K English stopwords equals open square bracket single quote a single quote comma single quote about single quote comma single quote above single quote comma single quote after single quote comma single quote again single quote comma single quote against single quote comma single quote ain single quote comma. single quote all single quote comma single quote am single quote comma single quote an single quote comma single quote and single quote single quote any single quote comma single quote are single quote comma single quote aren single quote comma double quotes aren single quote t double quotes comma single quote as single quote comma single quote at single quote comma. single quote be single quote comma single quote because single quote comma single quote been single quote comma single quote before single quote comma single quote being single quote comma single quote below single quote comma single quote between single quote comma single quote both single quote comma single quote but single quote comma single quote by single quote comma. single quote can single quote comma single quote couldn single quote comma double quotes couldn single quote t double quotes comma single quote d single quote comma single quote did single quote comma single quote didn single quote comma double quotes didn single quote t double quotes comma single quote do single quote comma single quote does single quote comma single quote doesn single quote comma. double quotes doesn single quote t double quotes comma single quote doing single quote comma single quote don single quote comma double quotes don single quote t double quotes comma single quote down single quote comma single quote during single quote comma single quote each single quote comma single quote few single quote comma single quote for single quote comma single quote from single quote comma. single quote further single quote comma single quote had single quote comma single quote hadn single quote comma double quotes hadn single quote t double quotes comma single quote has single quote comma single quote hasn single quote comma double quotes hasn single quote t double quotes comma single quote have single quote comma single quote haven single quote comma. double quotes haven single quote t double quotes comma single quote having single quote comma single quote he single quote comma double quotes he single quote d double quotes comma double quotes he single quote ll double quotes comma single quote her single quote comma single quote here single quote comma single quote hers single quote comma single quote herself single quote comma double quotes he single quote s double quotes comma. single quote him single quote comma single quote himself single quote comma single quote his single quote comma single quote how single quote comma single quote i single quote comma double quotes i single quote d double quotes comma single quote if single quote comma double quotes i single quote ll double quotes comma double quotes i single quote m double quotes comma single quote in single quote comma single quote into single quote comma single quote is single quote comma. single quote isn single quote comma double quotes isn single quote t double quotes comma single quote it single quote comma double quotes it single quote d double quotes comma double quotes it single quote ll double quotes comma double quotes it single quote s double quotes comma single quote its single quote comma single quote itself single quote comma double quotes i single quote ve double quotes comma single quote just single quote comma single quote 1l single quote comma. single quote m single quote comma single quote ma single quote comma single quote me single quote comma single quote mightn single quote comma double quotes mightn single quote t double quotes comma single quote more single quote comma single quote most single quote comma single quote mustn single quote comma double quotes mustn single quote t double quotes comma single quote my single quote comma. single quote myself single quote comma single quote needn single quote comma double quotes needn single quote t double quotes comma single quote no single quote comma single quote nor single quote comma single quote not single quote comma single quote now single quote comma single quote o single quote comma single quote of single quote comma single quote off single quote comma single quote on single quote comma. single quote once single quote comma single quote only single quote comma single quote or single quote comma single quote other single quote comma single quote our single quote comma single quote ours single quote comma single quote ourselves single quote comma single quote out single quote comma single quote over single quote comma single quote own single quote comma. single quote re single quote comma single quote s single quote comma single quote same single quote comma single quote shan single quote comma double quotes shan single quote t double quotes comma single quote she single quote comma double quotes she single quote d double quotes comma double quotes she single quote ll double quotes comma double quotes she single quote s double quotes comma single quote should single quote comma. single quote shouldn single quote comma double quotes shouldn single quote t double quotes comma double quotes should single quote ve double quotes comma double quotes so single quote comma single quote some single quote comma single quote such single quote comma single quote t single quote comma single quote than single quote comma single quote that single quote comma. double quotes that single quote ll double quotes comma single quote the single quote comma single quote their single quote comma single quote theirs single quote comma single quote them single quote comma single quote themselves single quote comma single quote then single quote comma single quote there single quote comma single quote these single quote comma. single quote they single quote comma double quotes they single quote d double quotes comma double quotes they single quote ll double quotes comma double quotes they single quote re double quotes comma double quotes they single quote ve double quotes comma single quote this single quote comma single quote those single quote comma single quote through single quote comma single quote to single quote comma. single quote too single quote comma single quote under single quote comma single quote until single quote comma single quote up single quote comma single quote ve single quote comma single quote very single quote comma single quote was single quote comma single quote wasn single quote comma double quotes wasn single quote t double quotes comma single quote we single quote comma double quotes we single quote d double quotes comma. double quotes we single quote ll double quotes comma double quotes we single quote re double quotes comma single quote were single quote comma single quote weren single quote comma double quotes weren single quote t double quotes comma double quotes we single quote ve double quotes comma single quote what single quote comma single quote when single quote comma single quote where single quote comma. single quote which single quote comma single quote while single quote comma single quote who single quote single quote whom single quote comma single quote why single quote comma single quote will single quote comma single quote with single quote comma single quote won single quote comma double quotes won single quote t double quotes. single quote wouldn single quote comma double quotes wouldn single quote t double quotes comma single quote y single quote comma single quote you single quote comma double quotes you single quote d double quotes comma double quotes you single quote ll double quotes comma single quote your single quote comma double quotes you single quote re double quotes comma single quote yours single quote comma. single quote yourself single quote comma single quote yourselves single quote comma double quotes you single quote ve double quotes close square bracket. At the bottom, another list of custom stopwords is displayed, including words such as: custom underscore stopwords equals open square bracket single quote employee single quote comma single quote employer single quote comma single quote emergency single quote comma single quote employees single quote comma single quote heat single quote comma single quote environment single quote comma single quote job single quote comma single quote temperature single quote comma single quote temperatures single quote comma single quote degree single quote comma single quote degrees single quote comma single quote health single quote comma single quote index single quote comma single quote Fahrenheit single quote comma single quote fahrenheit single quote comma single quote injury single quote comma single quote died single quote comma single quote injuries single quote comma single quote illness single quote comma single quote illnesses single quote comma single quote disease single quote comma single quote diseases single quote comma single quote project single quote comma single quote building single quote comma single quote construction single quote comma single quote exposure single quote comma single quote exposures single quote comma single quote exposed single quote comma single quote exposing single quote comma single quote environmental single quote comma single quote day single quote comma single quote due single quote comma single quote work single quote comma single quote incident single quote comma single quote person single quote comma single quote injured single quote close square bracket.

Full list of the stopwords and the NLTK preprocessing code. Source: Authors’ own work

or Create an Account

Close subscription notice
Close access options