Features by Category

447 features across 25 categories with 654 detection rules.

Adjective Modification (1)

Code Name Rules
COMPAR Comparatives 1

↑ Back to top

Adjective Semantics (15)

Semantic classes of adjectives (Biber 2006).

Code Name Rules
JJAPPEAR Adjectives of general appearance/physical attributes 2
JJATDother Attitudinal adjectives 1
JJCOLR Colour adjectives 1
JJCOMP Adjectives of comparison 2
JJEASE Adjectives of ease/difficulty 2
JJEPSTother Epistemic adjectives 2
JJEVAL Evaluative adjectives 3
JJIMP Adjectives of importance 2
JJJUDGE Adjectives of judgement/appearance 2
JJREL Relational adjectives 1
JJSHAPE Adjectives of shape 2
JJSIZE Size adjectives 1
JJTEXTR Adjectives of texture 2
JJTIME Temporal adjectives 1
JJTOPIC Topical adjectives 1

↑ Back to top

Adjectives (8)

Adjective features (attributive, predicative).

Code Name Rules
COMPSUP Comparative/superlative degrees 1
FAR_COMP Far + comparative adjective 1
JJAT Attributive adjectives 3
JJPR Predicative adjectives 3
JJR Comparative adjective forms 1
JJS Superlative adjective forms 1
MUCH_COMP Much + comparative adjective 1
SUPER Superlatives 1

↑ Back to top

Adverb Semantics (18)

Semantic classes of adverbs (Biber 2006).

Code Name Rules
LINORD Linear order 2
RATT Attitudinal adverbs 1
RBDEG Degree adverbs 2
RFACT Factive adverbs 1
RLIKELY Likelihood adverbs 1
RNONFACT Non-factive adverbs 1
SEM_FREQ Frequency/recurrence expressions 2
TBEGIN Time: beginning 1
TEARLY Time: early 2
TEND Time: ending 1
TFUTURE Time: future 2
TLATE Time: late 2
TMOMENT Time: momentary 1
TNEW Time: new/young 2
TOLD Time: old/mature 2
TPAST Time: past 2
TPERIOD Time: period 2
TPRESENT Time: present/simultaneous 2

↑ Back to top

Adverbials (7)

Adverb and adverbial expression features.

Code Name Rules
FREQ Frequency adverbs 2
PLACE Place adverbials 3
RB Other adverbs 3
RBAPPOS Adverbs introducing appositions 1
RBEXCL Exclusiviser/particulariser adverbs 2
RBPART Prepositional adverbs/particles 1
TIME Time adverbials 3

↑ Back to top

Adverbs (15)

Adverb features.

Code Name Rules
ACTUALLY Actually 2
BE_KIND_OF BE kind of / kinda + Adj 1
BE_SORT_OF BE sort of / sorta + Adj 1
CERT_ADV Epistemic certainty adverbs 1
INTENS_SO Intensifier so 1
IN_ADDITION In addition 2
IN_FACT In fact 2
JUDG_ADV Judgment adverbials 1
KIND_OF_N Kind of + N 1
NOT_JUST Not just 2
NOT_ONLY Not only 2
SORT_OF_N Sort of + N 1
WARDS_WORDS Words ending in -wards 1
WARD_WORDS Words ending in -ward 1
WHERE_WORDS Words ending in -where 1

↑ Back to top

Conjunctions (7)

Conjunction features (coordinating, subordinating).

Code Name Rules
ALTHOUGH Although 2
AS_IF As if 2
AS_THOUGH As though 2
THOUGH Though 2
TILL Till 2
UNTIL Until 2
WHETHER Whether 2

↑ Back to top

Derivational morphology (62)

Derivational prefixes and suffixes, following Bohmann (2019), Baayen (1994), and Biermeier (2008). Regex-based detection on word forms.

Code Name Rules
PREF_ANTI Prefix anti- 1
PREF_BE Prefix be- (verbal) 1
PREF_CO Prefix co- 1
PREF_CON Prefix con-/com- 1
PREF_COUNTER Prefix counter- 1
PREF_DE Prefix de- 1
PREF_DIS Prefix dis- 1
PREF_EN Prefix en- 1
PREF_EX Prefix ex- 1
PREF_INTER Prefix inter- 1
PREF_MIS Prefix mis- 1
PREF_PRE Prefix pre- 1
PREF_PRO Prefix pro- 1
PREF_RE Prefix re- 1
PREF_SEMI Prefix semi- 1
PREF_SPECI Prefix speci- 1
PREF_SPECT Prefix spect- 1
PREF_SPECU Prefix specu- 1
PREF_SUB Prefix sub-/sup- 1
PREF_SUPER Prefix super- 1
PREF_TRANS Prefix trans- 1
PREF_UN Prefix un- 1
PREF_UNDER_OVER Prefix under-/over- 1
PREF_UNI Prefix uni- 1
PREF_WITH Prefix with- 1
SUFF_ABLE Suffix -ible/-able 1
SUFF_AGE Suffix -age 1
SUFF_AL Suffix -al 1
SUFF_ANCE Suffix -ance 1
SUFF_ANT Suffix -ant 1
SUFF_ARY Suffix -ary 1
SUFF_ATION Suffix -ation 1
SUFF_DENT Suffix -dent 1
SUFF_DOM Suffix -dom 1
SUFF_EDLY Suffix V+ed+ly 1
SUFF_ER_OR Suffix -er/-or (agent nouns) 1
SUFF_FUL Suffix -ful 1
SUFF_HOOD Suffix -hood 1
SUFF_IAL Suffix -ial 1
SUFF_IAN Suffix -ian 1
SUFF_IC Suffix -ic 1
SUFF_ICAL Suffix -ical 1
SUFF_ICAN Suffix -ican 1
SUFF_IFY Suffix -ify 1
SUFF_ION Suffix -ion 1
SUFF_ISH Suffix -ish 1
SUFF_ISM Suffix -ism 1
SUFF_IST Suffix -ist 1
SUFF_ITY Suffix -ity 1
SUFF_IVE Suffix -ive 1
SUFF_IZE Suffix -ize 1
SUFF_LESS Suffix -less 1
SUFF_LIKE Suffix -like 1
SUFF_MENT Suffix -ment 1
SUFF_NESS Suffix -ness 1
SUFF_ORY Suffix -ory 1
SUFF_OUS Suffix -ous 1
SUFF_SHIP Suffix -ship 1
SUFF_TOR Suffix -tor 1
SUFF_TURE Suffix -ture 1
SUFF_ULAR Suffix -ular 1
SUFF_WISE Suffix -wise 1

↑ Back to top

Determinatives (7)

Determiners, quantifiers, demonstratives, genitives.

Code Name Rules
CD Cardinal numbers 1
DEMO Demonstrative determiners 2
DEMOP Demonstrative pronouns 3
DT Determiners 2
NUMERAL Numerals 1
POS S-genitives 1
QUAN Quantifiers 1

↑ Back to top

Determiners (5)

Determiner features.

Code Name Rules
A_LOT_OF A lot of 2
DEF_ART Definite article the 2
INDEF_ART Indefinite article a(n) 1
LOTS_OF Lots of 2
MANY_MUCH Many/much 1

↑ Back to top

Discourse Organization (26)

Conjunctions, subordination, relative clauses, questions, discourse markers.

Code Name Rules
CC Coordinating conjunctions 3
CONC Concessive conjunctions 2
COND Conditional conjunctions 3
CONJUNCTS Conjuncts 3
CUZ Causal conjunctions 3
DMA Discourse/pragmatic markers 3
ELAB Elaborating conjunctions 1
FPUH Filled pauses and interjections 2
LIKE like (non-verbal) 2
OTHADVSUB Other adverbial subordinators 2
QUTAG Question tags 2
SO so (residual) 2
SREL Sentence relatives 2
THADJ THAT clauses as adjective complements 2
THATD That deletion 4
THNC THAT clauses as noun complements 1
THRC That relative clauses on subject position 4
THRCO That relative clauses on object position 2
THRC_ALL That relative clauses (all) 1
THSC That subordinate clauses 2
WHQU Direct WH-questions 5
WHREL WH relative clauses 1
WHREL_OBJ WH relative clauses (object position) 2
WHREL_SUBJ WH relative clauses (subject position) 2
WHSC WH subordinate clauses 3
YNQU Yes/no questions 2

↑ Back to top

Function Words (69)

Individual function word frequencies, following stylometric tradition (Burrows, Mosteller & Wallace, Grieve 2023). Each feature measures the relative frequency of a single high-frequency function word.

Code Name Rules
FW_A Function word: "a" 1
FW_ALL Function word: "all" 1
FW_ALMOST Almost 1
FW_AN Function word: "an" 1
FW_AND Function word: "and" 1
FW_ARE Function word: "are" 1
FW_AS Function word: "as" 1
FW_AT Function word: "at" 1
FW_BE Function word: "be" 1
FW_BEEN Function word: "been" 1
FW_BUT Function word: "but" 1
FW_BY Function word: "by" 1
FW_COMPLETELY Completely 1
FW_CURRENTLY Currently 1
FW_ENTIRELY Entirely 1
FW_ESPECIALLY Especially 1
FW_FOR Function word: "for" 1
FW_FREQUENTLY Frequently 1
FW_FROM Function word: "from" 1
FW_HAD Function word: "had" 1
FW_HAS Function word: "has" 1
FW_HAVE Function word: "have" 1
FW_HER Function word: "her" 1
FW_HIM Function word: "him" 1
FW_HIS Function word: "his" 1
FW_I Function word: "i" 1
FW_IF Function word: "if" 1
FW_IMMEDIATELY Immediately 1
FW_IN Function word: "in" 1
FW_IS Function word: "is" 1
FW_IT Function word: "it" 1
FW_LIKELY Likely 1
FW_MAYBE Maybe 1
FW_MORE Function word: "more" 1
FW_NEARLY Nearly 1
FW_NO Function word: "no" 1
FW_NORMALLY Normally 1
FW_NOT Function word: "not" 1
FW_OF Function word: "of" 1
FW_OFTEN Often 1
FW_ON Function word: "on" 1
FW_ONE Function word: "one" 1
FW_OR Function word: "or" 1
FW_OUT Function word: "out" 1
FW_PARTICULARLY Particularly 1
FW_PERHAPS Perhaps 1
FW_PREVIOUSLY Previously 1
FW_PROBABLY Probably 1
FW_SHE Function word: "she" 1
FW_SOMETIMES Sometimes 1
FW_SUDDENLY Suddenly 1
FW_THAT Function word: "that" 1
FW_THE Function word: "the" 1
FW_THEIR Function word: "their" 1
FW_THERE Function word: "there" 1
FW_THEY Function word: "they" 1
FW_THIS Function word: "this" 1
FW_TO Function word: "to" 1
FW_USUALLY Usually 1
FW_WAS Function word: "was" 1
FW_WE Function word: "we" 1
FW_WERE Function word: "were" 1
FW_WHEN Function word: "when" 1
FW_WHICH Function word: "which" 1
FW_WHO Function word: "who" 1
FW_WILL Function word: "will" 1
FW_WITH Function word: "with" 1
FW_WOULD Function word: "would" 1
FW_YOU Function word: "you" 1

↑ Back to top

General Text Properties (5)

Text-level measures (word length, TTR, lexical density).

Code Name Rules
AWL Average word length 1
LDE Lexical density 1
MSL Mean sentence length 1
TTR Type-token ratio 1
WORDCOUNT Word count 1

↑ Back to top

Lexis (9)

Noun counts, noun compounds, nominalizations.

Code Name Rules
EMO Emoji and emoticons 1
GER Gerunds 2
HST Hashtags 1
NCOMP Noun compounds 2
NN Total other nouns 2
NNP Proper nouns 1
NN_ALL Total nouns (all) 1
NOMZ Nominalizations 2
URL URLs and email addresses 2

↑ Back to top

Modals (13)

Individual modal verbs and modal constructions.

Code Name Rules
ABLE BE ABLE TO 1
MDCA Modal CAN 3
MDCO Modal COULD 3
MDMM Modals MAY and MIGHT 2
MDNE Necessity modals 2
MDOU Modal OUGHT 2
MDSL Modal SHALL 2
MDWO Modal WOULD 3
MDWS Modals WILL and SHALL 2
POMD_ALL Possibility modals 2
PREDMD_ALL Predictive modals 2
WILL_CONT Contracted will ('ll) 1
WILL_FULL Uncontracted will 2

↑ Back to top

Negation (3)

Negation features (analytic and synthetic).

Code Name Rules
NEG_ALL Negation (all) 1
XX0 Analytic negation 3
XXSYN Synthetic negation 2

↑ Back to top

Noun Semantics (26)

Semantic classes of nouns (Biber 2006).

Code Name Rules
MEASURE Measurement expressions 2
NNABSPROC Abstract/process nouns 3
NNANIM Animate nouns 1
NNCLASS Nouns of classification 2
NNCOG Cognitive nouns 2
NNCOMM Common nouns 1
NNCOMMS Nouns of communications 1
NNCOMP Nouns of comparison 2
NNCONC Concrete nouns 3
NNEVAL Nouns of evaluation 2
NNGRP Group/institution nouns 3
NNHUMAN Human nouns 3
NNNUM Numeral nouns 2
NNPLACE Place nouns 4
NNPROP Proper nouns 1
NNQUANT Quantity/time nouns 1
NNSOCIAL Nouns of social actions/states/processes 1
NNSPEECH Nouns of speech acts 2
NNSUBS Nouns for substance/material 2
NNTECH Technical/scientific nouns 2
NNTEMP Temporal nouns 2
NSTNCother Stance nouns 1
SEMCOMPET Competition 2
SEMPERMIT Permission 2
SEMPOWER Power/organizing 1
SEMRESPECT Respect 2

↑ Back to top

Prepositions (4)

Preposition counts.

Code Name Rules
AMONG Among 2
AMONGST Amongst 2
IN Prepositions 3
PREP_SEQ Preposition sequences 1

↑ Back to top

Pronouns (20)

Personal, demonstrative, indefinite, and quantifying pronouns.

Code Name Rules
ARCH2P Archaic second person pronouns 1
DEMO_ALL Demonstratives (all) 1
EACHOTHER Each other 2
FPP First person pronouns 2
FPP1P First person plural pronouns 2
FPP1S First person singular pronouns 2
NPOSSPRO Nominal possessive pronouns 1
ONEANOTHER One another 2
PIT Pronoun IT 2
POSSPRO Possessive pronouns 1
PRP Pronoun ONE 1
QUPR Quantifying pronouns 2
REFPRO Reflexive pronouns 1
SPP2 Second person pronouns 2
TPP Third person pronouns 2
TPP3F Third person singular feminine pronouns 1
TPP3M Third person singular masculine pronouns 1
TPP3P Third person plural pronouns 2
TPP3S Third person singular pronouns 2
WHOM Whom 2

↑ Back to top

Stance (12)

Stance-taking devices: amplifiers, downtoners, emphatics, hedges, politeness.

Code Name Rules
AMP Amplifiers 3
DEFNEG Definite: negative 2
DEFPOS Definite: positive 2
DWNT Downtoners 3
EMPH Emphatics 3
HDG Hedges 3
POLITE Politeness markers 1
RBAPPROX Approximators 2
RBDIMIN Diminishers 2
RBINTNS Intensifiers (non-specific degree) 2
RBMAX Maximisers 2
RBMIN Minimisers 2

↑ Back to top

Stance Complement Patterns (28)

That-clauses, to-clauses, and WH-clauses subcategorised by the stance type of the preceding adjective, noun, or verb (Biber 2006).

Code Name Rules
PrepNSTNC Preposition after stance noun 1
ThJATT That-clause after attitudinal adjective 1
ThJEVL That-clause after evaluative adjective 1
ThJFCT That-clause after factive adjective 1
ThJLIK That-clause after likelihood adjective 1
ThNATT That-relative after attitudinal noun 1
ThNFCT That-relative after factive noun 1
ThNLIK That-relative after likelihood noun 1
ThNNFCT That-relative after non-factive noun 1
ThVATT That-clause after attitudinal verb 1
ThVCOMM That-clause after communication verb 1
ThVFCT That-clause after factive verb 1
ThVLIK That-clause after likelihood verb 1
ToJABL To-clause after ability adjective 1
ToJCRTN To-clause after certainty adjective 1
ToJEASE To-clause after ease adjective 1
ToJEFCT To-clause after factive adjective 1
ToJEVAL To-clause after evaluative adjective 1
ToNSTNC To-clause after stance noun 1
ToVDSR To-clause after desire verb 1
ToVEFRT To-clause after effort verb 1
ToVMNTL To-clause after mental verb 1
ToVPROB To-clause after probability verb 1
ToVSPCH To-clause after speech verb 1
WhVATT WH-clause after attitudinal verb 1
WhVCOM WH-clause after communication verb 1
WhVFCT WH-clause after factive verb 1
WhVLIK WH-clause after likelihood verb 1

↑ Back to top

Stative Forms (3)

Existential THERE and copular BE.

Code Name Rules
BEMA BE as main verb 3
EX Existential THERE 2
_EXTHERE Existential there + BE 1

↑ Back to top

Syntax (15)

Syntactic features: split auxiliaries, stranded prepositions, coordination, pied-piping.

Code Name Rules
COORD_PHRASAL Phrasal coordination 2
GERUND_COMP Verb + gerund complementation 1
HELP_TO Help + to-infinitive 1
INFAC Infinitive clauses as adjective complements 1
INFVC Infinitive clauses as verb complements 1
PIED Pied-piping constructions 3
PREVENT_FROM Prevent/stop + from 1
SPINF Split infinitives 1
SPLIT Split auxiliaries 2
SPLIT_ALL Split constructions (all) 2
STPR Stranded prepositions 2
S_GENITIVE S-genitive 1
TRY_AND Try and 1
TRY_TO Try to 1
WH_TOINF Wh + to-infinitive 1

↑ Back to top

Verb Features (43)

Verb morphology: tense, aspect, voice, contractions, particles.

Code Name Rules
BE_ABLE_TO BE able to 1
BE_ABOUT_TO BE about to 1
BE_SUPPOSED_TO BE supposed to 1
CONT Verbal contractions 3
GET_PASSIVE GET-passive 1
GOING_TO Going to (futurity) 1
GONNA Gonna 1
GOTTA Gotta 1
GTO Going-to future 1
HAVE_DEVERBAL HAVE + deverbal noun 1
HAVE_TO HAVE to (obligation) 1
HGOT HAVE got 2
IF_WAS If + was 1
IF_WERE If + were (subjunctive) 1
INFIN Infinitives 2
KEEP_VING KEEP V-ing 1
MAKE_DEVERBAL MAKE + deverbal noun 1
NEED_TO NEED to 1
PASS Agentless passives 4
PASSBY BY-passives 2
PASS_ALL Passives (all) 1
PAST_PERF Past perfect 1
PEAS Perfect aspect 4
PGET GET-passives 1
PROG Progressive aspect 3
PROG_ALWAYS Always-type progressive 1
PROG_PASS Progressive passive 1
REG_PAST Regularised verbal past forms 1
RP Verb particles 1
STRONG_PAST Strong verbal past forms 1
TAKE_DEVERBAL TAKE + deverbal noun 1
VBD Past tense 1
VBG Non-finite -ing forms (all) 2
VBG_CLAUSE Present participial clauses 2
VBN Non-finite -ed forms (all) 2
VBN_CLAUSE Past participial clauses 2
VIMP Imperatives 2
VPRT Present tense 1
WANNA Wanna 1
WANT_TO WANT to 1
WHIZBG Present participial WHIZ deletions 2
WHIZBN Past participial WHIZ deletions 2
WILL_PROG Will + progressive 1

↑ Back to top

Verb Semantics (26)

Semantic verb classes (activity, mental, communication, etc.).

Code Name Rules
ACT Activity verbs 1
ASPECT Aspectual verbs 1
CAUSE Causative/facilitation verbs 1
COMM Communication verbs 2
DOAUX DO auxiliary 2
DOPV Pro-verb DO 1
EXIST Existential/relationship verbs 2
MENTAL Mental verbs 2
OCCUR Occurrence verbs 1
SEMHELP Helping 2
SEMHINDER Hindrance 2
SENSE Sensory verbs 2
SUASIVE Suasive verbs 2
VATTother Attitudinal verbs (other contexts) 1
VBABST General/abstract verbs of being/existing 1
VBCLASS Verbs of classification 2
VBCOMP Verbs of comparison 2
VBEVAL Verbs of evaluation 2
VBMOD Verbs of modification/change 2
VBSOCIAL Verbs of social actions/states/processes 1
VBSPEECH Verbs of speech acts 2
VBSTAT Verbs of remaining/inactivity 2
VCOMMother Communication verbs (other contexts) 1
VFCTother Factive verbs (other contexts) 1
VLIKother Likelihood verbs (other contexts) 1
_INFDO Infinitival DO (helper) 1

↑ Back to top