Word Frequency Measures Research Articles

Measuring Phonological Complexity Using the Perfect Rhymes Dictionary (PeRDict)

This paper examines links between perfect rhymes and text readability and decoding using a measure of English rhymes called the Perfect Rhymes Dictionary (PeRDict). PeRDict is based on the Carnegie Mellon University Pronouncing Dictionary (the CMUdict) and provides rhyme counts for ∼48,000 words in English and for the most frequent 1,000, 2,500, 5,000, and 10,000 rhymes within the dictionary as measured by the Corpus of American English (COCA). Two assessments of PeRDICT are presented. The first examines the strength of rhyme features to predict text readability in conjunction with word neighborhood density effects reported by the English Lexicon Project (ELP) and a word frequency measure. The second examines the strength of rhyme features to predict word decoding in conjunction with word neighborhood effects and a word frequency measure. In both assessments, the number of rhymes per word was predictive of text or word processing beyond features related to word neighborhood effects and word frequency. Word rhyme counts performed more strongly in predicting text processing versus word processing.

Timed picture naming norms for 800 photographs of 200 objects in English

The present study presents picture-naming norms for a large set of 800 high-quality photographs of 200 natural objects and artefacts spanning a range of categories, with four unique images per object. Participants were asked to provide a single, most appropriate name for each image seen. We report recognition latencies for each image, and several normed variables for the provided names: agreement, H-statistic (i.e. level of naming uncertainty), Zipf word frequency and word length. Rather than simply focusing on a single name per image (i.e. the modal or most common name), analysis of recognition latencies showed that it is important to consider the diversity of labels that participants may ascribe to each pictured object. The norms therefore provide a list of candidate labels per image with weighted measures of word length and frequency per image that incorporate all provided names, as well as modal measures based on the most common name only.

Lexical and sub-lexical frequencies in isiXhosa-medium children’s stories

Visual word recognition in developing readers is affected by several factors, many of which are important in the design of teaching and testing materials. Among these, one well-studied factor is word frequency: more frequent words are recognised more quickly than less frequent words. Another is the presence of consonant sequences, where words containing a consonant sequence (e.g. ‘tsh’) are recognised more slowly than non-consonant-sequence-containing words of equivalent letter and phoneme length. In isiXhosa, there are currently no publicly available word frequency norms that are based on children’s literacy materials and are thus appropriate for the testing of developing readers. Publicly available information on the frequencies of particular consonant sequences, which would be valuable in the design of classroom materials, is also lacking. To address these gaps, this paper reports on the creation of a corpus of isiXhosa texts aimed at children (321 texts, 125,447 tokens, and 31,216 types), which was subsequently processed to derive (i) word frequency measures, (ii) descriptive statistics about the characteristics of the most frequent words, and (iii) information on sublexical frequency, with a focus on two-, three-, and four-consonant sequences. The findings of the article are relevant to scholars and practitioners working on literacy development and language processing in isiXhosa.

The utility of neuropsychological process scores in verbal recall and verbal fluency in persons with or at risk for dementia: Data from COMPASS‐ND

AbstractBackgroundSubjective cognitive decline (SCD) is considered a risk state for decline to mild cognitive impairment (MCI) or dementia due to Alzheimer’s disease (AD). By definition, individuals with SCD report concerns about changes in cognitive function but perform within normal limits on formal testing. This study examined whether neuropsychology process scores on tests of auditory learning and memory (the Rey Auditory Verbal Learning Test, RAVLT) and semantic and phonemic oral fluency were able to distinguish subtle difficulties in cognition, over and above total scores.MethodWe used data from the Comprehensive Assessment of Neurodegeneration and Dementia (COMPASS‐ND) study to examine performance in 60 cognitively normal (CN) older adults with no cognitive complaints (mean age = 69 years; mean education = 16 years), 55 participants with SCD (age = 70; education = 17), 102 with MCI (age = 72; education = 16), and 47 with AD (age = 75; education = 15). Participants were matched on age and education, except for AD participants who were older. Age and education were co‐variates in all analyses. For the RAVLT, we examined delayed recall total scores, and process measures of primacy and recency recall on the second learning trial. For fluency, we examined total scores, and process measures of clustering, switching, word frequency, and age of acquisition.ResultRAVLT: An item position by group interaction revealed that primacy scores better distinguished all participant groups (CU>SCD>MCI>AD) than delayed recall (CU = SCD = MCI>AD). The left subiculum hippocampal subfield volume was positively associated with primacy scores in the MCI group, controlling for intracranial volume and age. Oral fluency: Both phonemic and semantic total scores discriminated CN, MCI, and AD participants in a stepwise manner; there was a non‐significant trend for SCD participants to perform more poorly than CN. Process scores did not provide additional discrimination.ConclusionThese findings indicate that primacy scores for episodic recall are sensitive to subtle memory deficits in SCD and may reflect hippocampal atrophy, supporting the clinical use of using serial position effects in the assessment of MCI and SCD.Learning Objective(s): Participants will learn about more detailed scoring methods for common neuropsychological tests, their sensitivity to subtle cognitive deficits in SCD, and their relationship with neuroanatomical structures.

YouTube Transcripts Word Frequency Measure

Many YouTube videos provide written audio transcripts which provide information on the language used on YouTube. One important measure relating to language usage is word frequency. Using student-developed software and libraries in R, Python, and Microsoft Excel, the transcripts of one million YouTube videos from the YouTube-8M data set were scraped and analyzed. The word frequency of the YouTube data set was shown to correlate with commonly used word frequency measures from established studies, such as the subtitle word frequency and the HAL word frequency.

The Flickr frequency norms: What 17 years of images tagged online tell us about lexical processing.

Word frequency is one of the best predictors of language processing. Typically, word frequency norms are entirely based on natural-language text data, thus representing what the literature typically refers to as purely linguistic experience. This study presents Flickr frequency norms as a novel word frequency measure from a domain-specific corpus inherently tied to extra-linguistic information: words used as image tags on social media. To obtain Flickr frequency measures, we exploited the photo-sharing platform Flickr Image (containing billions of photos) and extracted the number of uploaded images tagged with each of the words considered in the lexicon. Here, we systematically examine the peculiarities of Flickr frequency norms and show that Flickr frequency is a hybrid metrics, lying at the intersection between language and visual experience and with specific biases induced by being based on image-focused social media. Moreover, regression analyses indicate that Flickr frequency captures additional information beyond what is already encoded in existing norms of linguistic, sensorimotor, and affective experience. Therefore, these new norms capture aspects of language usage that are missing from traditional frequency measures: a portion of language usage capturing the interplay between language and vision, which - this study demonstrates - has its own impact on word processing. The Flickr frequency norms are openly available on the Open Science Framework(https://osf.io/2zfs3/).

The Power of Leadership Artistry

We introduce leadership artistry as a promising approach in contemporary leadership studies. While we know leaders should rely on innovation, courage, and aspiration more than on duplicating historical patterns of pragmatism for leadership decision-making under uncertainty, we know little about how these processes achieve. In this paper, we define leadership artistry as a subject aspect of the leadership attributes and characterize its dimensions which are distinct from other leadership approaches. Additionally, we propose a semi-supervised machine learning approach to create an artistry dictionary. Finally, by applying a weighted word frequency measure, we illustrate that corporate top management team's leadership artistry does impact firm creativity performance, furthering our contribution to theory and practice.

Linguistic complexity in teachers' assessment of German essays in high stakes testing

In national educational standards, linguistic complexity is one of the core aspects characterizing the demands of reading material and student writing quality. In Germany, teachers are supposed to consider linguistic complexity in their assessment of language arts Abitur examinations, the high stakes test qualifying for higher education admission in Germany. In the present study, we investigated if and how teachers consider linguistic complexity in their assessment of writing quality. To systematically identify a range of linguistic complexity aspects, we conducted computational linguistic analyses of student essays (N = 344) written during Abitur examinations in the subject German. Experienced teachers (N = 33) then regraded a subsample of the essays (n = 16) and rated their linguistic complexity. We used mixed-effects models to study the relationships between computational measures of linguistic complexity, teachers’ assessment of writing quality (language, content, and overall grade), and their linguistic complexity rating. Results confirm that teachers’ complexity rating and their assessment of the language aspect of writing quality is related to the computed linguistic complexity features, primarily measures of syntactic complexity and language use (word frequency measures). But findings also show that teachers have difficulties in separating linguistic complexity from aspects of content and language accuracy.

Shabd: A psycholinguistic database for Hindi.

We present Shabd, a psycholinguistic database in Hindi. It is based on a corpus of 1.4 billion words from electronic newspapers and news websites. Word frequencies and part of speech information have been derived and are made available in a cleaned list of 34 thousand hand-selected words, and a list of 96 thousand words observed with a frequency of more than 100 times in the corpus. Next to the Shabd database, we also make a list with all 2.3 million word types available and a list with the 2.5 million most frequent word pairs (word bigrams). The quality of the word frequency measure was tested in two lexical decision tasks. We observed that the Shabd word frequencies outperform existing frequencies based on smaller corpora of newspapers but not the Worldlex word frequencies based on an analysis of blogs. We also observed that word frequency accounts for as much variance as contextual diversity (operationalized as the number of documents in which the words were observed). The Shabd database is freely available for research.

A novel corpus developed to evaluate the impact of hospital noise on speech intelligibility

Hospital noise often exceeds recommended sound levels set by health organizations leading to reductions in speech intelligibility and communication breakdowns between doctors and patients. However, quantifying the impact of hospital noise on intelligibility has been limited by stimuli employed in prior studies, which did not include medically related terminology. To address this gap, a corpus of medically related sentences was developed. Word frequency, word familiarity, and sentence predictability, factors known to impact intelligibility of speech, were quantified. Nearly 700 words were selected from the Merriam-Webster Medical Dictionary. Word frequency was taken from Lexique, a 51-million-word corpus of American subtitles (Brysbaert & New, 2009). Word familiarity was rated by 41 monolingual listeners. The words were then used to construct 200 sentences. To determine sentence predictability, the sentences were presented to 48 participants with one word missing; their task was to fill in the missing word. Three 40 item sentence sets with different familiarity / frequency types (low/low, high/low, high/high) were selected, all with low predictability levels. These sentences and 40 standard speech perception sentences were recorded by two male and two female talkers. This corpus can be used to assess how hospital noise impacts intelligibility across listener populations. Brysbaert, M., & New, B. (2009). Moving beyond Kučera and Francis: A critical evaluation of current word frequency norms and the introduction of a new and improved word frequency measure for American English. Behavior Research Methods, 41, 977-990. doi:10.3758/BRM.41.4.977.

Analysis and Classification of Word Co-Occurrence Networks From Alzheimer’s Patients and Controls

In this paper we construct word co-occurrence networks from transcript data of controls and patients with potential Alzheimer’s disease using the ADReSS challenge dataset of spontaneous speech. We examine measures of the structure of these networks for significant differences, finding that networks from Alzheimer’s patients have a lower heterogeneity and centralization, but a higher edge density. We then use these measures, a network embedding method and some measures from the word frequency distribution to classify the transcripts into control or Alzheimer’s, and to estimate the cognitive test score of a participant based on the transcript. We find it is possible to distinguish between the AD and control networks on structure alone, achieving 66.7% accuracy on the test set, and to predict cognitive scores with a root mean squared error of 5.675. Using the network measures is more successful than using the network embedding method. However, if the networks are shuffled we find relatively few of the measures are different, indicating that word frequency drives many of the network properties. This observation is borne out by the classification experiments, where word frequency measures perform similarly to the network measures.

An Analysis of Text Difficulty across Grades in Korean Middle School English Textbooks Using Coh-Metrix

This study aims to investigate the text difficulty of the reading materials of Korean middle school English textbooks with Coh-Metrix, a software developed by the Institute for Intelligent Systems at the University of Memphis to analyze the linguistic and psycholinguistic features of English text and textbooks with a wide range of indices on cohesion and language. In this study, the textbook corpus consisted of the text files extracted from 13 English textbooks. These files were used for analyzing the text difficulty among grades with Coh-Metrix. The Coh-Metrix indices selected for this study contained basic counts, word frequency, word features, lexical diversity, pronouns, connectives, readability, syntax complexity, syntax similarity, reference cohesion, semantic cohesion, and situation model measures. The results showed that there were significant differences among grades for basic counts, word features, first pronouns, causal and temporal connectives, readability, reference and semantic cohesion, the number of words before main verbs, syntactic similarity, and situation model measures. The differences among grades, however, were not significant for word frequency, lexical diversity, second and third person pronouns, additive connectives, and NP density measures. The findings have educational implications for textbook design and language learning for English learners.

한국어 분석 시스템 Auto-Kohesion을 활용한 고등학교 국어교과서에 수록된 서사문과 논설문 비교 분석

This study aims to analyze the linguistic and psycholinguistic differences between narrative and argumentative materials of high school Korean textbooks with Auto-Kohesion, a computer program designed to investigate Korean texts by a wide range of measures. The results show that the higher proportion of modifiers and the use of more pronouns (the second and the third person pronouns) are noticeable in the narrative texts. For all word frequency measures, the average word frequency in the narrative texts is lower than in the argumentative texts. Also, the reference cohesion (noun overlap for adjacent sentences and total sentences), the syntactic complexity, the average sentence length, and the average word length are relatively higher in the narrative texts. These results have several pedagogical implications for the development of Korean textbooks and Korean language teaching materials.

Social roles and structural signatures of top influentials in the #prayforparis Twitter network

Scholars have shown much interest in whether diffusion is inflated through planting a piece of information by influential people (influentials). Although a few attempts have been made to discover structural gaps or gap fillers in the Twitter network, these efforts mainly concentrated on applying topological approaches to detect influentials in online networks. Further, though many studies explored diffusion on the Twitter network, they rarely examined the phenomenon with a theoretical framework. Through the #prayforparis Twitter network, this study attempted (1) to identify top influentials by applying multiple centrality measures and word frequency measures and (2) to examine social roles based on structural signatures of the Twitter network through the lens of the Diffusion of Innovation Theory. To fulfill the objectives of this study, the authors employed an innovative multi-method approach combining Social Network Analysis, word frequency analysis via NodeXL and R, and a qualitative approach to examine behavioral and structural relationships of the #prayforparis Twitter network. Top influentials of the network were pop music celebrities who shared condolences to the victims of the 2015 Paris attacks through their tweets. This study identified “celebrity” and “fan” as social roles based on the structural and qualitative analysis of the network as well as metrical examinations, including indegree and outdegree counts of the social roles of the “celebrities” and “fans.” Justin Bieber, the most dominant influential individual in the #prayforparis Twitter network, functioned as a breaking news provider through his tweet about the death of his friend during the Paris attacks. By filling the gap from the past studies, this study utilizes the theoretical improvement in the diffusion research as well as contributes to the methodological approach about influentials and social roles in the Twitter network.

Linguistic entrenchment and the effect of subjective lexical familiarity in Korean /n/-insertion

Korean shows variable /n/-insertion between a morpheme-final consonant and the initial /i/ or /j/ of a following morpheme. Literature has shown that the appearance of the phenomenon can be affected by various parameters, including social and phonological factors. Exemplar theory contends that a word’s susceptibility to language variation correlates directly with its word frequency, a unitary frequency measure based on a corpus (Pierrehumbert 2001; Bybee 2002). However, given that individuals have different language experience, word frequency rarely addresses individual differences in the same way that self-rated measures of word frequency, known as subjective lexical familiarity, do. This research investigates whether and how the metric of self-rated lexical familiarity affects Korean /n/-insertion. Results indicate that subjective lexical familiarity significantly predicts the appearance of /n/-insertion, such that words more familiar to the speaker show /n/-insertion more often than those that are less familiar.

MEGALEX: A megastudy of visual and auditory word recognition.

Using the megastudy approach, we report a new database (MEGALEX) of visual and auditory lexical decision times and accuracy rates for tens of thousands of words. We collected visual lexical decision data for 28,466 French words and the same number of pseudowords, and auditory lexical decision data for 17,876 French words and the same number of pseudowords (synthesized tokens were used for the auditory modality). This constitutes the first large-scale database for auditory lexical decision, and the first database to enable a direct comparison of word recognition in different modalities. Different regression analyses were conducted to illustrate potential ways to exploit this megastudy database. First, we compared the proportions of variance accounted for by five word frequency measures. Second, we conducted item-level regression analyses to examine the relative importance of the lexical variables influencing performance in the different modalities (visual and auditory). Finally, we compared the similarities and differences between the two modalities. All data are freely available on our website ( https://sedufau.shinyapps.io/megalex/ ) and are searchable at www.lexique.org , inside the Open Lexique search engine.

Computerized Analysis of Verbal Fluency: Normative Data and the Effects of Repeated Testing, Simulated Malingering, and Traumatic Brain Injury.

In verbal fluency (VF) tests, subjects articulate words in a specified category during a short test period (typically 60 s). Verbal fluency tests are widely used to study language development and to evaluate memory retrieval in neuropsychiatric disorders. Performance is usually measured as the total number of correct words retrieved. Here, we describe the properties of a computerized VF (C-VF) test that tallies correct words and repetitions while providing additional lexical measures of word frequency, syllable count, and typicality. In addition, the C-VF permits (1) the analysis of the rate of responding over time, and (2) the analysis of the semantic relationships between words using a new method, Explicit Semantic Analysis (ESA), as well as the established semantic clustering and switching measures developed by Troyer et al. (1997). In Experiment 1, we gathered normative data from 180 subjects ranging in age from 18 to 82 years in semantic (“animals”) and phonemic (letter “F”) conditions. The number of words retrieved in 90 s correlated with education and daily hours of computer-use. The rate of word production declined sharply over time during both tests. In semantic conditions, correct-word scores correlated strongly with the number of ESA and Troyer-defined semantic switches as well as with an ESA-defined semantic organization index (SOI). In phonemic conditions, ESA revealed significant semantic influences in the sequence of words retrieved. In Experiment 2, we examined the test-retest reliability of different measures across three weekly tests in 40 young subjects. Different categories were used for each semantic (“animals”, “parts of the body”, and “foods”) and phonemic (letters “F”, “A”, and “S”) condition. After regressing out the influences of education and computer-use, we found that correct-word z-scores in the first session did not differ from those of the subjects in Experiment 1. Word production was uniformly greater in semantic than phonemic conditions. Intraclass correlation coefficients (ICCs) of correct-word z-scores were higher for phonemic (0.91) than semantic (0.77) tests. In semantic conditions, good reliability was also seen for the SOI (ICC = 0.68) and ESA-defined switches in semantic categories (ICC = 0.62). In Experiment 3, we examined the performance of subjects from Experiment 2 when instructed to malinger: 38% showed abnormal (p< 0.05) performance in semantic conditions. Simulated malingerers with abnormal scores could be distinguished with 80% sensitivity and 89% specificity from subjects with abnormal scores in Experiment 1 using lexical, temporal, and semantic measures. In Experiment 4, we tested patients with mild and severe traumatic brain injury (mTBI and sTBI). Patients with mTBI performed within the normal range, while patients with sTBI showed significant impairments in correct-word z-scores and category shifts. The lexical, temporal, and semantic measures of the C-VF provide an automated and comprehensive description of verbal fluency performance.

The Chinese Lexicon Project: A megastudy of lexical decision performance for 25,000+ traditional Chinese two-character compound words.

Using a megastudy approach, we developed a database of lexical variables and lexical decision reaction times and accuracy rates for more than 25,000 traditional Chinese two-character compound words. Each word was responded to by about 33 native Cantonese speakers in Hong Kong. This resource provides a valuable adjunct to influential mega-databases, such as the Chinese single-character, English, French, and Dutch Lexicon Projects. Three analyses were conducted to illustrate the potential uses of the database. First, we compared the proportion of variance in lexical decision performance accounted for by six word frequency measures and established that the best predictor was Cai and Brysbaert's (PLoS One, 5, e10729, 2010) contextual diversity subtitle frequency. Second, we ran virtual replications of three previously published lexical decision experiments and found convergence between the original experiments and the present megastudy. Finally, we conducted item-level regression analyses to examine the effects of theoretically important lexical variables in our normative data. This is the first publicly available large-scale repository of behavioral responses pertaining to Chinese two-character compound word processing, which should be of substantial interest to psychologists, linguists, and other researchers.

On the advantages of word frequency and contextual diversity measures extracted from subtitles: The case of Portuguese.

We examined the potential advantage of the lexical databases using subtitles and present SUBTLEX-PT, a new lexical database for 132,710 Portuguese words obtained from a 78 million corpus based on film and television series subtitles, offering word frequency and contextual diversity measures. Additionally we validated SUBTLEX-PT with a lexical decision study involving 1920 Portuguese words (and 1920 nonwords) with different lengths in letters (M = 6.89, SD = 2.10) and syllables (M = 2.99, SD = 0.94). Multiple regression analyses on latency and accuracy data were conducted to compare the proportion of variance explained by the Portuguese subtitle word frequency measures with that accounted by the recent written-word frequency database (Procura-PALavras; P-PAL; Soares, Iriarte, et al., 2014 ). As its international counterparts, SUBTLEX-PT explains approximately 15% more of the variance in the lexical decision performance of young adults than the P-PAL database. Moreover, in line with recent studies, contextual diversity accounted for approximately 2% more of the variance in participants' reading performance than the raw frequency counts obtained from subtitles. SUBTLEX-PT is freely available for research purposes (at http://p-pal.di.uminho.pt/about/databases ).

A fresh look at the predictors of naming accuracy and errors in Alzheimer's disease

In recent years, a considerable number of studies have tried to establish which characteristics of objects and their names predict the responses of patients with Alzheimer's disease (AD) in the picture-naming task. The frequency of use of words and their age of acquisition (AoA) have been implicated as two of the most influential variables, with naming being best preserved for objects with high-frequency, early-acquired names. The present study takes a fresh look at the predictors of naming success in Spanish and English AD patients using a range of measures of word frequency and AoA along with visual complexity, imageability, and word length as predictors. Analyses using generalized linear mixed modelling found that naming accuracy was better predicted by AoA ratings taken from older adults than conventional ratings from young adults. Older frequency measures based on written language samples predicted accuracy better than more modern measures based on the frequencies of words in film subtitles. Replacing adult frequency with an estimate of cumulative (lifespan) frequency did not reduce the impact of AoA. Semantic error rates were predicted by both written word frequency and senior AoA while null response errors were only predicted by frequency. Visual complexity, imageability, and word length did not predict naming accuracy or errors.