Using Sensing Tools to Examine Talk Within Locations of the Early Childhood Inclusive Classroom

• In Event: Using Sensing Technologies to Understand Children's Experiences in Early Childhood Education Classrooms

Abstract

Using an advanced sensing system to enhance our understanding of inclusion has both advantages and challenges. I will present snapshots of three example studies that captured talk and location data in early childhood inclusive classrooms (e.g., how data were collected, data generated through the sensor systems used). I will provide information on the training and skills needed to use the technology, as well as a look behind the curtain: what went right, what could have gone better, and what can be learned from the studies below:

Study 1: We piloted the combining of two wearable sensor technologies (i.e., the Language ENvironmental Analysis [LENA] and Ubisense) to advance our understanding of the adult and peer talk a preschooler with a developmental delay experienced in classroom activity areas. The LENA is an automated recording and processing measure of adult, child, and peer talk, and Ubisense is a real-time location system (RTLS). The marrying of these novel technologies has the potential to move beyond existing direct observational and global quality approaches and provide objective information about children’s individual experiences in the classroom. Findings include the distribution of time and speech captured in activity areas of the classroom in reference to the focal child and an illustration of adult talk displayed in a heat map (see Figure 1). Overall, certain areas of the classroom (e.g., Art) appeared to yield more talk than others.

Study 2: We used Ubisense and an advanced speech processing approach (i.e., combined speech-activity detection and speaker diarization, or Combo-SAD) to capture features of friendship – child-peer speech and proximity within activity areas – for a focal child at-risk for a disability. Our preliminary results indicate the focal child and each playmate spent time vocalizing near one another across 4 activity areas. Additionally, compared to the Blocks activity area, the children had significantly lower odds of talking while in proximity during Manipulatives and Science. This suggests that the activity areas children occupy may affect their engagement with peers and, in turn, the friendships they development.

Study 3: The use of wh-words, including wh-questions and wh-clauses, can be linguistically, conceptually, and interactively challenging to preschoolers (e.g., Deshmukh et al, 2019). Young children develop mastery of wh-words as they formulate and hear these words during daily interactions in contexts such as preschool classrooms (e.g., Cabell et al., 2015). We report the results of the first study using Ubisense coupled with an automated speech recognition (ASR) system designed to quantify teachers' wh-words in literacy activity areas of a preschool classroom. We found that the ASR system is a viable solution to automatically quantify the number of adult wh-words used in preschool classrooms. Our findings demonstrated that the most frequently used adult wh-word type was "what." Classroom adults used more wh-words during time point 1 compared to time point 2. Lastly, a child at risk for developmental delays heard more wh-words per minute than a typically developing child.

In addition to the above, we discuss next steps in using sensing technologies in the early childhood inclusive classroom.

Author

• Dwight Irvin, University of Kansas
  Presenting Author