Search for: All records

Influence operations are large-scale efforts to manipulate public opinion. The rapid detection and disruption of these operations is critical for healthy public discourse. Emergent AI technologies may enable novel operations that evade detection and influence public discourse on social media with greater scale, reach, and specificity. New methods of detection with inductive learning capacity will be needed to identify novel operations before they indelibly alter public opinion and events. To this end, we develop an inductive learning framework that: (1) determines content- and graph-based indicators that are not specific to any operation; (2) uses graph learning to encode abstract signatures of coordinated manipulation; and (3) evaluates generalization capacity by training and testing models across operations originating from Russia, China, and Iran. We find that this framework enables strong cross-operation generalization while also revealing salient indicators-illustrating a generic approach which directly complements transductive methodologies, thereby enhancing detection coverage. 

Over half of US children are enrolled in preschools, where the quantity and quality of language input from teachers are likely to affect children's language development. Leveraging repeated objective measurements, we examined the rate per minute and phonemic diversity of child and teacher speech‐related vocalizations in preschool classrooms and their association with children's end‐of‐year receptive and expressive language abilities measured with the Preschool Language Scales (PLS‐5). Phonemic diversity was computed as the number of unique consonants and vowels in a speech‐related vocalization. We observed three successive cohorts of 2.5–3.5‐year‐old children enrolled in an oral language classroom that included children with and without hearing loss (N = 29, 16 girls, 14 Hispanic). Vocalization data were collected using child‐worn audio recorders over 34 observations spanning three successive school years, yielding 21.53 mean hours of audio recording per child. The rate of teacher vocalizations positively predicted the rate of children's speech‐related vocalizations while the phonemic diversity of teacher vocalizations positively predicted the phonemic diversity of children's speech‐related vocalizations. The phonemic diversity of children's speech‐related vocalizations was a stronger predictor of end‐of‐year language abilities than the rate of children's speech‐related vocalizations. Mediation analyses indicated that the phonemic diversity of teacher vocalizations was associated with children's receptive and expressive language abilities to the extent that it influenced the phonemic diversity of children's own speech‐related vocalizations. The results suggest that qualitatively richer language input expands the phonemic diversity of children's speech, which in turn is associated with language abilities.