Figures
1.1The relationship between the relative frequency of adjectives and verbs
1.4The distribution of the first-person pronoun in the Trinity Lancaster Corpus
1.16Top ten places connected with ‘going’ or ‘travelling’ in the BNC
1.18The use of adjectives by fiction and academic writers: boxplot
1.19The use of adjectives by fiction and academic writers: error bars
3.2Collocation graph: ‘love’ in BE06 (10a – log Dice (7), L3–R3, C5–NC5)
3.4Third-order collocates of time in LOB (3a–MI(5), R5–L5, C4–NC4; no filter applied)
3.5Collocation network of ‘university’ based on BE06 (3b–MI(3), L5–R5, C8–NC8)
3.6Collocation networks around ‘immigrants’ in the Guardian (3a–MI(6), R5–L5, C10–NC10; no filter applied)
3.7Collocation networks around ‘immigrants’ in the Daily Mail (3a–MI(6), R5–L5, C20–NC20; no filter applied)
4.2The vs a(n) dataset: linguistic feature design (an excerpt)
4.7Visualization of the relationship between which and that and a separator
5.6Statistically significant (p <0.05) Pearson’s correlations in relation to the number of observations
5.7Multi-panel scatterplot: nouns, adjectives, verbs, pronouns and coordinators
5.8Correlation matrix: nouns, adjectives, verbs, pronouns and coordinators
5.12Colour terms: a tree plot (dendrogram) – z-score2 normalized, Euclidean distance, SLINK method
5.17A dataset for multidimensional analysis (a small extract)
5.21Mean scores of registers placed on Dimension 1: Involved vs Informational
5.23Correlation between mean word length and contractions: register clusters
5.27Relationship between mean word length (number of characters) and mean sentence length (number of words) in BNC
5.28Relationship between the use of the past and the present tense in BE06
5.29Relationship between the use of adjectives and colour terms in BE06
5.30Relationship between text length (tokens) and type–token ratio (TTR) in BNC
6.1Distribution of personal pronouns in BNC64 female speakers
6.2ANOVA calculation: between-group variance (top), within-group variance (bottom)
6.3Dataset from BNC64 – relative frequencies and ranks: use of personal pronouns
6.4Distribution of ain’t in BNC64 speakers: social-class effect
6.6A correspondence plot: word classes in the speech of individual speakers
6.9Sociolinguistic dataset: internal and external factors (an excerpt)
6.11Correspondence analysis: use of word classes by White House press secretaries
6.12Correspondence analysis: use of epistemic markers in BNC64
7.2Modals in the Brown family corpora: an alternative interpretation
7.4Modals in the Brown family corpora: original (top) and rescaled (bottom)
7.5Modals in British English: (a) boxplots; (b) 95% CI error bars
7.6Candlestick plot: the development of individual modals 1931–2006
7.10Two clustering principles: (a) hierarchical agglomerative clustering; (b) variability-based neighbour clustering
7.11Dendrograms: (a) hierarchical agglomerative clustering; (b) variability-based neighbour clustering
7.12Dendrogram: use of the possessive pronoun its in the seventeenth century
7.13Scree plot: use of the possessive pronoun its in the seventeenth century
7.14Resulting peaks and troughs graphs: settings as indicated
7.15Results of UFA for war 1940–2009 (3a–MI(3), L5–R5, C10relative–NC10relative; AC1)
7.18Results of UFA for red 1600–99 (3a–MI(3), L5–R5, C10relative–NC10relative; AC1)
7.20Number of tweets related to an episode of the UK X-Factor (16/11/2014, 7–11pm)
7.21Development of frequencies of handsome, pretty and beautiful followed by a male (M) or female (F) person in the seventeenth century
7.22Development of frequencies of the possessive pronoun its in the seventeenth century
8.3Past tense (a) and present tense (b) in different written genres of BE06: boxplot rendition
