No abstract

Purpose The algorithm of the Language ENvironment Analysis (LENA) system for calculating language environment measures was trained on American English; thus, its validity with other languages cannot be assumed. This article evaluates the accuracy of the LENA system applied to Korean. Method We sampled sixty 5-min recording clips involving 38 key children aged 7–18 months from a larger data set. We establish the identification error rate, precision, and recall of LENA classification compared to human coders. We then examine the correlation between standard LENA measures of adult word count, child vocalization count, and conversational turn count and human counts of the same measures. Results Our identification error rate (64% or 67%), including false alarm, confusion, and misses, was similar to the rate found in Cristia, Lavechin, et al. (2020) . The correlation between LENA and human counts for adult word count ( r = .78 or .79) was similar to that found in the other studies, but the same measure for child vocalization count ( r = .34–.47) was lower than the value in Cristia, Lavechin, et al., though it fell within ranges found in other non-European languages. The correlation between LENA and human conversational turn count was not high ( r = .36–.47), similar to the findings in other studies. Conclusions LENA technology is similarly reliable for Korean language environments as it is for other non-English language environments. Factors affecting the accuracy of diarization include speakers' pitch, duration of utterances, age, and the presence of noise and electronic sounds.

No abstract

This study examined the caregiver's role as an initiator of conversational interactions and the effects of such a role on infants’ word learning. 228 daylong LENA recordings from 141 Korean mother-child dyads (60 girls & 81 boys aged 7-30 months) were analysed. Both the child and mother showed more engaging patterns of speech behavior in their own-initiated conversational blocks across ages. Analysis of 40 children at an early speech stage (15 girls; aged 14-15 months) showed that mothers of children with higher CDI percentile initiated more conversation and responded more quickly. Mothers of at-risk children provided less response to the child’s vocalization than typically developing children, and mothers who provided a greater ratio of response also initiated more conversation.

Fig. 1. Star Wars Day creative visuals collected on Twitter from (a) McDonald's, (b) Volkswagen, and (c) Girl ScoutsPop culture is a pervasive and important aspect of communication and self-expression. When people wish to communicate using pop culture references, they need to find connections between their message and the things, people, location and actions of a movie, tv series, or other pop culture domain. However, finding an appropriate match from memory is challenging and search engines are not specific enough to the task. Often domain-specific knowledge graphs provide the structure, specificity and search capabilities that people need. We introduce PopNet -a Pop Culture Knowledge Association Network automatically created from plain text using state-of-the art NLP methods to extract entities and actions from text summaries of movies and tv shows. The interface allows people to browse and search the entries to find connections. We conduct a study showing that this system is accurate and helpful for finding multiple connections between a message and a pop culture domain.CCS Concepts: • Human-centered computing → Interactive systems and tools.