Feature Overview

The table below gives an overview of the implemented features in ELFEN, grouped by feature area, with details on the feature name, description, and the feature area it belongs to.

Feature	Feature Area	Feature name	Name in extracted dataframe	Function	Description	Notes
Raw sequence length/total number of characters	surface	raw_sequence_length	raw_sequence_length	get_raw_sequence_length	Number of characters in the text (including whitespaces)
Number of tokens	surface	n_tokens	n_tokens	get_num_tokens	Number of tokens in the text
Number of sentences	surface	n_sentences	n_sentences	get_num_sentences	Number of sentences in the text
Number of token per sentence	surface	tokens_per_sentence	tokens_per_sentence	get_num_tokens_per_sentence	Average number of tokens per sentence: n_tokens / n_sentences
Number of characters	surface	n_characters	n_characters	get_num_characters	Number of characters in the text (excluding whitespaces)
Characters per sentence	surface	characters_per_sentence	characters_per_sentence	get_chars_per_sentence	Average number of characters per sentence: n_characters / n_sentences
Raw sequence length per sentence	surface	raw_length_per_sentence	raw_length_per_sentence	get_raw_length_per_sentence	Average number of characters per sentence: raw_sequence_length / n_sentences
Average word length	surface	avg_word_length	avg_word_length	get_avg_word_length	Average word length (in characters): n_characters / n_tokens
Number of types	surface	n_types	n_types	get_num_types	Number of types (unique tokens) in the text
Number of long words	surface	n_long_words	n_long_words	get_num_long_words	Number of long words (i.t.o. characters)	Threshold of what is considered a long word defaults to >6 characters; can be adapted in the config
Number of lemmas	surface	n_lemmas	n_lemmas	get_num_lemmas	Number of lemmas in the text
Token frequencies	surface	token_freqs	token_freqs	get_token_freqs	Token frequencies of the types in the text	As this produces a list in a column, writing to file has to be handled
Number of lexical tokens	pos	n_lexical_tokens	n_lexical_tokens	get_num_lexical_tokens	Number of lexical tokens (tokens w/ upos tag NOUN, ADVERB, ADJ, ADV)
POS variability	pos	pos_variability	pos_variability	get_pos_variability	POS variability of the text: (unique upos text in the text) / n_tokens
Number of tokens with upos tag {pos}	pos	n_per_pos	n_{pos}	get_num_per_pos	Number of tokens with a given upos tag in the text. Takes a list of upos tag to extract this feature for	pos_list defaults to all upos tags; if you only need a subset, this can be adapted in the config
Lemma token ratio	lexical_richness	lemma_token_ratio	lemma_token_ratio	get_lemma_token_ratio	Lemma token ratio of the text: n_lemmas / n_tokens
Type token ratio	lexical_richness	ttr	ttr	get_ttr	Type token ratio of the text: n_types / n_tokens
Root type token ratio	lexical_richness	rttr	rttr	get_rttr	Root type token ratio of the text: sqrt(n_types / n_tokens)
Corrected type token ratio	lexical_richness	cttr	cttr	get_cttr	Corrected type token ratio of the text: n_types / sqrt(2 * n_tokens)
Herdan’s C	lexical_richness	herdan_c	herdan_c	get_herdan_c	Herdan’s C of a text: log(n_types) / log(n_tokens)
Summer’s type token ratio/ index	lexical_richness	summer_index	summer_index	get_summer_index	Summer’s text token ratio of the text: log(log(n_types)) / log(log(n_tokens))
Dugast’s Uber index	lexical_richness	dugast_u	dugast_u	get_dugast_u	Dugast’s Uber index of the text: log(n_types)^2 / (log(n_tokens) - log( n_types))
Maas’ text token ratio/index	lexical_richness	maas_index	maas_index	get_maas_index	Maas’ text token ratio of the text: (n_tokens - n_types) / log(n_types)^2
Number of local hapax legomena	lexical_richness	n_hapax_legomena	n_hapax_legomena	get_n_hapax_legomena	Number of hapax legomena (tokens that occur only once) in the text
Number of global token hapax legomena	lexical_richness	n_global_token_hapax_legomena	n_global_token_hapax_legomena	get_n_global_token_hapax_legomena	Number of hapax legomena (tokens that occur only once) in the entire corpus in the text instance
Number of global lemma hapax legomena	lexical_richness	n_global_lemma_hapax_legomena	n_global_lemma_hapax_legomena	get_n_global_lemma_hapax_legomena	Number of hapax legomena (lemmas that occur only once) in the entire corpus in the text instance
Number of hapax dislegomena	lexical_richness	n_hapax_dislegomena	n_hapax_dislegomena	get_n_hapax_dislegomena	Number of hapax dislegomena (tokens that occur once or twice) in the text
Number of global token hapax dislegomena	lexical_richness	n_global_token_hapax_dislegomena	n_global_token_hapax_dislegomena	get_n_global_token_hapax_dislegomena	Number of hapax dislegomena (tokens that occur once or twice) in the entire corpus in the text instance
Number of global lemma hapax dislegomena	lexical_richness	n_global_lemma_hapax_dislegomena	n_global_lemma_hapax_dislegomena	get_n_global_lemma_hapax_dislegomena	Number of hapax dislegomena (tokens that occur once or twice) in the entire corpus in the text instance
Sichel’s S	lexical_richness	sichel_s	sichel_s	get_sichel_s	Sichel’s S of the text: n_hapax_dislegomena / n_types
Global Sichel’s S	lexical_richness	global_sichel_s	global_sichel_s	get_global_sichel_s	Global Sichel’s S of the text: n_global_token_hapax_dislegomena / n_types
Lexical density	lexical_richness	lexical_density	lexical_density	get_lexical_density	Lexical density of the text: n_lexical_tokens / n_tokens
Giroud’s index	lexical_richness	giroud_index	giroud_index	get_giroud_index	Giroud’s index of a text: n_types / sqrt(n_tokens)
Measure of Textual Lexical Density (MTLD)	lexical_richness	mtld	mtld	get_mtld	For definition, check https://link.springer.com/article/10.3758/BRM.42.2.381
Hypergeometric Distribution Diversity (HD-D	lexical_richness	hdd	hdd	get_hdd	For definition, check https://link.springer.com/article/10.3758/BRM.42.2.381
Moving-average type token ratio (MATTR)	lexical_richness	mattr	mattr	get_mattr	Calculates the TTR for a sliding window of n tokens, then takes the average
Mean segmental type token ratio (MSTTR)	lexical_richness	msttr	msttr	get_msttr	Divides the text into n segments, calculates the TTR for all of them, then takes the average
Yule’s K	lexical_richness	yule_k	yule_k	get_yule_k	Yule’s characteristic constant of vocabulary richness	For definition, check https://quantling.org/~hbaayen/publications/TweedieBaayen1998.pdf
Simpson’s D	lexical_richness	simpsons_d	simpsons_d	get_simpsons_d		For definition, check https://quantling.org/~hbaayen/publications/TweedieBaayen1998.pdf
Herdan’s Vm	lexical_richness	herdan_v	herdan_v	get_herdan_v		For definition, check https://quantling.org/~hbaayen/publications/TweedieBaayen1998.pdf
Number of syllables	readability	n_syllables	n_syllables	get_num_syllables	Number of syllables in the text	Only implemented for spacy backbone
Number of monosyllables	readability	n_monosyllables	n_monosyllables	get_num_monosyllables	Number of monosyllables (words with only one syllable) in the text
Number of polysyllables	readability	n_polysyllables	n_polysyllables	get_num_polysyllables	Number of polysyllables (words with three or more syllables) in the text
Flesch reading ease	readability	flesch_reading_ease	flesch_reading_ease	get_flesch_reading_ease	Flesch reading ease score of the text	For reference: https://en.wikipedia.org/wiki/Flesch%E2%80%93Kincaid_readability_tests#Flesch_Reading_Ease
Flesch-Kincaid Grade Level	readability	flesch_kincaid_grade	flesch_kincaid_grade	get_flesch_kincaid_grade	Flesch-Kincaid grade level of the text	For reference: https://en.wikipedia.org/wiki/Flesch%E2%80%93Kincaid_readability_tests#Flesch.E2.80.93Kincaid_Grade_Level
Automated Readability Index (ARI)	readability	ari	ari	get_ari		For reference: https://en.wikipedia.org/wiki/Automated_readability_index
Simple Measure of Gobbledygook (SMOG)	readability	smog	smog	get_smog		For reference: https://en.wikipedia.org/wiki/SMOG
Coleman-Liau Index (CLI)	readability	cli	cli	get_cli		For reference: https://en.wikipedia.org/wiki/Coleman%E2%80%93Liau_index
Gunning-fog Index	readability	gunning_fog	gunning_fog	get_gunning_fog		For reference: https://en.wikipedia.org/wiki/Gunning_fog_index
LIX	readability	lix	lix	get_lix		For reference: https://en.wikipedia.org/wiki/Lix_(readability_test)
RIX	readability	rix	rix	get_rix		For reference: https://www.jstor.org/stable/40031755
Compressibility	information	compressibility	compressibility	get_compressibility	Compressibility is the ratio of the length of the compressed text to the length of the original text. This is a proxy for the Kolmogorov complexity of the text
Entropy	information	entropy	entropy	get_entropy	Shannon entropy of the text
Number of named entities	entities	n_entitites	n_entitites	get_num_entities	Number of named entities in the text
Number of named entities of type {ent}	entities	n_per_entity_type	n_{ent}	get_num_per_entity_type	Number of named entities in the text with type {ent}. Takes a list of entity types to extract this feature for	ent_types defaults to all possible entity types; if you only need a subset, this can be adapted in the config
Number of hedge words	semantic	n_hedges	n_hedges	get_num_hedges	Number of hedge words in the text (words expressing uncertainty of the speaker).	requires a hedge lexicon; currently only supported in English
Hedges token ratio	semantic	hedges_ratio	hedges_ratio	get_hedges_ratio	Ratio of hedges in the text: n_hedges / n_tokens
Average number of synsets	semantic	avg_n_synsets	avg_n_synsets	get_avg_num_synsets	Average number of wordnet synsets of lexical tokens; proxy for ambiguity/polysemy
Number of words with a low number of synsets per pos	semantic	n_low_synsets_per_pos	n_low_synsets_{pos}	get_low_synsets_{pos}	Number of lexical tokens with a low number of synsets per pos tag	Threshold defaults to 2
Number of words with a high number of synsets per pos	semantic	n_high_synsets_per_pos	n_high_synsets_{pos}	get_high_synsets_{pos}	Number of lexical tokens with a high number of synsets per pos tag	Threshold defaults to 5
Number of words with a low number of synsets	semantic	n_low_synsets	n_low_synsets	get_num_low_synsets	Number of lexical tokens with a low number of synsets	Threshold defaults to 2
Number of words with a high number of synsets	semantic	n_high_synsets	n_high_synsets	get_num_high_synsets	Number of lexical tokens with a high number of synsets	Threshold defaults to 5
Average valence	emotion	avg_valence	avg_valence	get_avg_valence	Average valence of the tokens in the text	For reference: https://saifmohammad.com/WebPages/nrc-vad.html
Number of low valence tokens	emotion	n_low_valence	n_low_valence	get_n_low_valence	Number of low valence tokens in the text	Threshold defaults to 0.33; For reference: https://saifmohammad.com/WebPages/nrc-vad.html
Number of high valence tokens	emotion	n_high_valence	n_high_valence	get_n_high_valence	Number of high valence tokens in the text	Threshold defaults to 0.66; For reference: https://saifmohammad.com/WebPages/nrc-vad.html
Average arousal	emotion	avg_arousal	avg_arousal	get_avg_arousal	Average arousal of the tokens in the text	For reference: https://saifmohammad.com/WebPages/nrc-vad.html
Maximum arousal	emotion	max_arousal	max_arousal	get_max_arousal	Maximum arousal of the tokens in the text	For reference: https://saifmohammad.com/WebPages/nrc-vad.html
Minimum arousal	emotion	min_arousal	min_arousal	get_min_arousal	Minimum arousal of the tokens in the text	For reference: https://saifmohammad.com/WebPages/nrc-vad.html
Standard deviation of arousal	emotion	sd_arousal	sd_arousal	get_sd_arousal	Standard deviation of the arousal ratings of the tokens in the text	For reference: https://saifmohammad.com/WebPages/nrc-vad.html
Number of low arousal tokens	emotion	n_low_arousal	n_low_arousal	get_n_low_arousal	Number of low arousal tokens in the text	Threshold defaults to 0.33; For reference: https://saifmohammad.com/WebPages/nrc-vad.html
Number of high arousal tokens	emotion	n_high_arousal	n_high_arousal	get_n_high_arousal	Number of high arousal tokens in the text	Threshold defaults to 0.66; For reference: https://saifmohammad.com/WebPages/nrc-vad.html
Maximum dominance	emotion	max_dominance	max_dominance	get_max_dominance	Maximum dominance of the tokens in the text	For reference: https://saifmohammad.com/WebPages/nrc-vad.html
Minimum dominance	emotion	min_dominance	min_dominance	get_min_dominance	Minimum dominance of the tokens in the text	For reference: https://saifmohammad.com/WebPages/nrc-vad.html
Standard deviation of dominance	emotion	sd_dominance	sd_dominance	get_sd_dominance	Standard deviation of the dominance ratings of the tokens in the text	For reference: https://saifmohammad.com/WebPages/nrc-vad.html
Average dominance	emotion	avg_dominance	avg_dominance	get_avg_dominance	Average dominance of the tokens in the text	For reference: https://saifmohammad.com/WebPages/nrc-vad.html
Number of low dominance tokens	emotion	n_low_dominance	n_low_dominance	get_n_low_dominance	Number of low dominance tokens in the text	Threshold defaults to 0.33; For reference: https://saifmohammad.com/WebPages/nrc-vad.html
Number of high dominance tokens	emotion	n_high_dominance	n_high_dominance	get_n_high_dominance	Number of high dominance tokens in the text	Threshold defaults to 0.66; For reference: https://saifmohammad.com/WebPages/nrc-vad.html
Maximum emotion intensity for {emotion}	emotion	max_intensity	max_intensity_{emotion}	get_max_intensity	Maximum intensity of an emotion; takes a list of emotions	For reference: https://saifmohammad.com/WebPages/AffectIntensity.htm
Minimum emotion intensity for {emotion}	emotion	min_intensity	min_intensity_{emotion}	get_min_intensity	Minimum intensity of an emotion; takes a list of emotions	For reference: https://saifmohammad.com/WebPages/AffectIntensity.htm
Standard deviation of emotion intensity for {emotion}	emotion	sd_intensity	sd_intensity_{emotion}	get_sd_intensity	Standard deviation of intensity of an emotion; takes a list of emotions	For reference: https://saifmohammad.com/WebPages/AffectIntensity.htm
Average emotion intensity for {emotion}	emotion	avg_intensity	avg_intensity_{emotion}	get_avg_intensity	Average intensity of an emotion; takes a list of emotions	For reference: https://saifmohammad.com/WebPages/AffectIntensity.htm
Number of high intensity tokens for {emotion}	emotion	n_high_intensity	n_high_intensity_{emotion}	get_n_high_intensity	Number of high intensity tokens for a given emotion	Threshold defaults to 0.33; For reference: https://saifmohammad.com/WebPages/AffectIntensity.htm
Number of low intensity tokens for {emotion}	emotion	n_low_intensity	n_low_intensity_{emotion}	get_n_low_intensity	Number of high§§ intensity tokens for a given emotion	Threshold defaults to 0.66; For reference: https://saifmohammad.com/WebPages/AffectIntensity.htm
Maximum intensity for {emotion}	emotion	max_{emotion}	max_{emotion}	get_max_{emotion}	Maximum value for a given emotion; takes a list of emotions	For reference: https://saifmohammad.com/WebDocs/NRC-Emotion-Lexicon.htm
Minimum intensity for {emotion}	emotion	min_{emotion}	min_{emotion}	get_min_{emotion}	Minimum value for a given emotion; takes a list of emotions	For reference: https://saifmohammad.com/WebDocs/NRC-Emotion-Lexicon.htm
Standard deviation of intensity for {emotion}	emotion	sd_{emotion}	sd_{emotion}	get_sd_{emotion}	Standard deviation of values for a given emotion; takes a list of emotions	For reference: https://saifmohammad.com/WebDocs/NRC-Emotion-Lexicon.htm
Sentiment score	emotion	sentiment_score	sentiment_score	get_sentiment_score	Difference between the number of positive and negative sentiment words in the text: (n_positive_sentiment - n_negative_sentiment) / n_tokens	Values in range (-1,1) where 0 is neutral, -1 is completely negative sentiment, and 1 is completely positive sentiment; For reference: https://saifmohammad.com/WebDocs/NRC-Emotion-Lexicon.htm
Number of negative sentiment tokens	emotion	n_negative_sentiment	n_negative_sentiment	get_n_negative_sentiment	Number of negative sentiment tokens	For reference: https://saifmohammad.com/WebPages/NRC-Emotion-Lexicon.htm
Number of positive sentiment tokens	emotion	n_positive_sentiment	n_positive_sentiment	get_n_positive_sentiment	Number of positive sentiment tokens	For reference: https://saifmohammad.com/WebDocs/NRC-Emotion-Lexicon.htm
Average concreteness	psycholinguistic	avg_concreteness	avg_concreteness	get_avg_concreteness	Average human concreteness ratings of the tokens in the text	For reference: https://link.springer.com/article/10.3758/s13428-013-0403-5
Average standard deviation of concreteness	psycholinguistic	avg_sd_concreteness	avg_sd_concreteness	get_avg_sd_concreteness	Average standard deviation in the human concreteness ratings of the tokens in the text	For reference: https://link.springer.com/article/10.3758/s13428-013-0403-5
Number of low concreteness tokens	psycholinguistic	n_low_concreteness	n_low_concreteness	get_n_low_concreteness	Number of tokens with a low concreteness rating	For reference: https://link.springer.com/article/10.3758/s13428-013-0403-5
Number of high concreteness tokens	psycholinguistic	n_high_concreteness	n_high_concreteness	get_n_high_concreteness	Number of tokens with a high concreteness rating	For reference: https://link.springer.com/article/10.3758/s13428-013-0403-5
Number of tokens with controversial concreteness	psycholinguistic	n_controversial_concreteness	n_controversial_concreteness	get_n_controversial_concreteness	Number of tokens with a high standard deviation in the human concreteness rating	For reference: https://link.springer.com/article/10.3758/s13428-013-0403-5
Maximum concreteness	psycholinguistic	max_concreteness	max_concreteness	get_max_concreteness	Maximum concreteness rating of the tokens in the text	For reference: https://link.springer.com/article/10.3758/s13428-013-0403-5
Minimum concreteness	psycholinguistic	min_concreteness	min_concreteness	get_min_concreteness	Minimum concreteness rating of the tokens in the text	For reference: https://link.springer.com/article/10.3758/s13428-013-0403-5
Standard deviation of concreteness	psycholinguistic	sd_concreteness	sd_concreteness	get_sd_concreteness	Standard deviation of the concreteness ratings of the tokens in the text	For reference: https://link.springer.com/article/10.3758/s13428-013-0403-5
Average age of acquisition	psycholinguistic	avg_aoa	avg_aoa	get_avg_aoa	Average age of acquisition rating	For reference: https://link.springer.com/article/10.3758/s13428-016-0811-4
Average standard deviation of age of acquisition	psycholinguistic	avg_sd_aoa	avg_sd_aoa	get_avg_sd_aoa	Average standard deviation in the age of acquisition rating	For reference: https://link.springer.com/article/10.3758/s13428-016-0811-4
Number of low age of acquisition tokens	psycholinguistic	n_low_aoa	n_low_aoa	get_n_low_aoa	Number of low age of acquisition tokens	For reference: https://link.springer.com/article/10.3758/s13428-016-0811-4
Number of high age of acquisition tokens	psycholinguistic	n_high_aoa	n_high_aoa	get_n_high_aoa	Number of high age of acquisition tokens	For reference: https://link.springer.com/article/10.3758/s13428-016-0811-4
Number of tokens with controversial age of acquisition	psycholinguistic	n_controversial_aoa	n_controversial_aoa	get_n_controversial_aoa	Number of tokens with a high standard deviation in the age of acquisition rating	For reference: https://link.springer.com/article/10.3758/s13428-016-0811-4
Minimum age of acquisition	psycholinguistic	min_aoa	min_aoa	get_min_aoa	Minimum age of acquisition rating of the tokens in the text	For reference: https://link.springer.com/article/10.3758/s13428-016-0811-4
Maximum age of acquisition	psycholinguistic	max_aoa	max_aoa	get_max_aoa	Maximum age of acquisition rating of the tokens in the text	For reference: https://link.springer.com/article/10.3758/s13428-016-0811-4
Standard deviation of age of acquisition	psycholinguistic	sd_aoa	sd_aoa	get_sd_aoa	Standard deviation of the age of acquisition ratings of the tokens in the text	For reference: https://link.springer.com/article/10.3758/s13428-016-0811-4
Average prevalence	psycholinguistic	avg_prevalence	avg_prevalence	get_avg_prevalence	Average human prevalence ratings of the tokens in the text	For reference: https://link.springer.com/article/10.3758/s13428-018-1077-9
Number of low prevalence tokens	psycholinguistic	n_low_prevalence	n_low_prevalence	get_n_low_prevalence	Number of low prevalence tokens	For reference: https://link.springer.com/article/10.3758/s13428-018-1077-9
Number of high prevalence tokens	psycholinguistic	n_high_prevalence	n_high_prevalence	get_n_high_prevalence	Number of high prevalence tokens	For reference: https://link.springer.com/article/10.3758/s13428-018-1077-9
Minimum prevalence	psycholinguistic	min_prevalence	min_prevalence	get_min_prevalence	Minimum prevalence rating of the tokens in the text	For reference: https://link.springer.com/article/10.3758/s13428-018-1077-9
Maximum prevalence	psycholinguistic	max_prevalence	max_prevalence	get_max_prevalence	Maximum prevalence rating of the tokens in the text	For reference: https://link.springer.com/article/10.3758/s13428-018-1077-9
Standard deviation of prevalence	psycholinguistic	sd_prevalence	sd_prevalence	get_sd_prevalence	Standard deviation of the prevalence ratings of the tokens in the text	For reference: https://link.springer.com/article/10.3758/s13428-018-1077-9
Average socialness	psycholinguistic	avg_socialness	avg_socialness	get_avg_socialness	Average human socialness ratings of the tokens in the text	For reference: https://link.springer.com/article/10.3758/s13428-022-01810-x
Average standard deviation of socialness	psycholinguistic	avg_sd_socialness	avg_sd_socialness	get_avg_sd_socialness	Average standard deviation in the human socialness ratings of the tokens in the text	For reference: https://link.springer.com/article/10.3758/s13428-022-01810-x
Number of high socialness tokens	psycholinguistic	n_high_socialness	n_high_socialness	get_n_high_socialness	Number of high socialness tokens	For reference: https://link.springer.com/article/10.3758/s13428-022-01810-x
Number of low socialness tokens	psycholinguistic	n_low_socialness	n_low_socialness	get_n_low_socialness	Number of low socialness tokens	For reference: https://link.springer.com/article/10.3758/s13428-022-01810-x
Number of tokens with controversial socialness	psycholinguistic	n_controversial_socialness	n_controversial_socialness	get_n_controversial_socialness	Number of tokens with a high standard deviation in the human socialness rating	For reference: https://link.springer.com/article/10.3758/s13428-022-01810-x
Minimum socialness	psycholinguistic	min_socialness	min_socialness	get_min_socialness	Minimum socialness rating of the tokens in the text	For reference: https://link.springer.com/article/10.3758/s13428-022-01810-x
Maximum socialness	psycholinguistic	max_socialness	max_socialness	get_max_socialness	Maximum socialness rating of the tokens in the text	For reference: https://link.springer.com/article/10.3758/s13428-022-01810-x
Standard deviation of socialness	psycholinguistic	sd_socialness	sd_socialness	get_sd_socialness	Standard deviation of the socialness ratings of the tokens in the text	For reference: https://link.springer.com/article/10.3758/s13428-022-01810-x
Average iconicity	psycholinguistic	avg_iconicity	avg_iconicity	get_avg_iconicity	Average human iconicity ratings of the tokens in the text	For reference: https://link.springer.com/article/10.3758/s13428-023-02112-6
Average standard deviation of iconicity	psycholinguistic	avg_sd_iconicity	avg_sd_iconicity	get_avg_sd_iconicity	Average standard deviation in the human iconicity ratings of the tokens in the text	For reference: https://link.springer.com/article/10.3758/s13428-023-02112-6
Number of high iconicity tokens	psycholinguistic	n_high_iconicity	n_high_iconicity	get_n_high_iconicity	Number of high iconicity tokens	For reference: https://link.springer.com/article/10.3758/s13428-023-02112-6
Number of low iconicity tokens	psycholinguistic	n_low_iconicity	n_low_iconicity	get_n_low_iconicity	Number of low iconicity tokens	For reference: https://link.springer.com/article/10.3758/s13428-023-02112-6
Number of tokens with controversial iconicity	psycholinguistic	n_controversial_iconicity	n_controversial_iconicity	get_n_controversial_iconicity	Number of tokens with a high standard deviation in the human iconicity rating	For reference: https://link.springer.com/article/10.3758/s13428-023-02112-6
Minimum iconicity	psycholinguistic	min_iconicity	min_iconicity	get_min_iconicity	Minimum iconicity rating of the tokens in the text	For reference: https://link.springer.com/article/10.3758/s13428-023-02112-6
Maximum iconicity	psycholinguistic	max_iconicity	max_iconicity	get_max_iconicity	Maximum iconicity rating of the tokens in the text	For reference: https://link.springer.com/article/10.3758/s13428-023-02112-6
Standard deviation of iconicity	psycholinguistic	sd_iconicity	sd_iconicity	get_sd_iconicity	Standard deviation of the iconicity ratings of the tokens in the text	For reference: https://link.springer.com/article/10.3758/s13428-023-02112-6
Average sensorimotor score for {sensorimotor}	psycholinguistic	avg_sensorimotor	avg_{var}_sensorimotor	get_avg_sensorimotor	Average sensorimotor score for a given sensorimotor dimension
Average standard deviation of sensorimotor score	psycholinguistic	avg_sd_sensorimotor	avg_sd_{var}_sensorimotor	get_avg_sd_sensorimotor	Average standard deviation in the sensorimotor scores of the tokens in the text
Number of tokens with low sensorimotor rating	psycholinguistic	n_low_sensorimotor	n_low_{var}_sensorimotor	get_n_low_sensorimotor	Number of tokens with low sensorimotor rating
Number of tokens with high sensorimotor rating	psycholinguistic	n_high_sensorimotor	n_high_{var}_sensorimotor	get_n_high_sensorimotor	Number of tokens with high sensorimotor rating
Number of tokens with controversial sensorimotor rating	psycholinguistic	n_controversial_sensorimotor	n_controversial_{var}_sensorimotor	get_n_controversial_sensorimotor	Number of tokens with a high standard deviation in the sensorimotor rating
Minimum sensorimotor score	psycholinguistic	min_sensorimotor	min_{var}_sensorimotor	get_min_sensorimotor	Minimum sensorimotor rating of the tokens in the text
Maximum sensorimotor score	psycholinguistic	max_sensorimotor	max_{var}_sensorimotor	get_max_sensorimotor	Maximum sensorimotor rating of the tokens in the text
Standard deviation of sensorimotor score	psycholinguistic	sd_sensorimotor	sd_{var}_sensorimotor	get_sd_sensorimotor	Standard deviation of the sensorimotor ratings of the tokens in the text
Morphological feature counts	morphological	n_per_morph_feature	n_{pos}_{feature}_{val}	get_morph_feats	Number of tokens with {pos} {feature} {val} (e.g. VERB VerbForm Inf), takes a dictionary of pos and associated features and values for them	Default dictionary is the full set of UD options; adapt if you do not need all of them (may be language-specific)
Dependency tree width	dependency	tree_width	tree_width	get_tree_width	Maximum number of siblings of a node at any level
Dependency tree depth	dependency	tree_depth	tree_depth	get_tree_depth	Maximum distance of a token to the root of the dependency tree
Tree branching factor	dependency	tree_branching	tree_branching	get_tree_branching	Average number of children of a token in the dependency tree
Tree ramification factor	dependency	ramification_factor	ramification_factor	get_ramification_factor	Average number of children per level
Number of noun chunks	dependency	n_noun_chunks	n_noun_chunks	get_n_noun_chunks	Number of noun chunks in the dependency tree
Number of dependencies of type {type}	dependency	n_per_dependency_type	n_dependency_{type}	get_n_per_dependency_type
{Feature} token ratio	ratios/normalization		{feature}_token_ratio	get_feature_token_ratio
{Feature} type ratio	ratios/normalization		{feature}_type_ratio	get_feature_type_ratio
{Feature} sentence ratio	ratios/normalization		{feature}_sentence ratio	get_feature_sentence_ratio