Exploratory analysis of real personal emergency response call conversations: considerations for personal emergency response spoken dialogue systems

Journal of NeuroEngineering and Rehabilitation, Nov 2016

Background The purpose of this study was to derive data from real, recorded, personal emergency response call conversations to help improve the artificial intelligence and decision making capability of a spoken dialogue system in a smart personal emergency response system. The main study objectives were to: develop a model of personal emergency response; determine categories for the model’s features; identify and calculate measures from call conversations (verbal ability, conversational structure, timing); and examine conversational patterns and relationships between measures and model features applicable for improving the system’s ability to automatically identify call model categories and predict a target response. Methods This study was exploratory and used mixed methods. Personal emergency response calls were pre-classified according to call model categories identified qualitatively from response call transcripts. The relationships between six verbal ability measures, three conversational structure measures, two timing measures and three independent factors: caller type, risk level, and speaker type, were examined statistically. Results Emergency medical response services were the preferred response for the majority of medium and high risk calls for both caller types. Older adult callers mainly requested non-emergency medical service responders during medium risk situations. By measuring the number of spoken words-per-minute and turn-length-in-words for the first spoken utterance of a call, older adult and care provider callers could be identified with moderate accuracy. Average call taker response time was calculated using the number-of-speaker-turns and time-in-seconds measures. Care providers and older adults used different conversational strategies when responding to call takers. The words ‘ambulance’ and ‘paramedic’ may hold different latent connotations for different callers. Conclusions The data derived from the real personal emergency response recordings may help a spoken dialogue system classify incoming calls by caller type with moderate probability shortly after the initial caller utterance. Knowing the caller type, the target response for the call may be predicted with some degree of probability and the output dialogue could be tailored to this caller type. The average call taker response time measured from real calls may be used to limit the conversation length in a spoken dialogue system before defaulting to a live call taker.

A PDF file should load here. If you do not see its contents the file may be temporarily unavailable at the journal website or you do not have a PDF plug-in installed and enabled in your browser.

Alternatively, you can download the file locally and open with any standalone PDF reader:

http://www.jneuroengrehab.com/content/pdf/s12984-016-0207-9.pdf

Exploratory analysis of real personal emergency response call conversations: considerations for personal emergency response spoken dialogue systems

Young et al. Journal of NeuroEngineering and Rehabilitation Exploratory analysis of real personal emergency response call conversations: considerations for personal emergency response spoken dialogue systems Victoria Young 0 1 4 Elizabeth Rochon 0 1 4 6 Alex Mihailidis 0 1 2 3 4 5 0 University Health Network - Toronto Rehabilitation Institute , Toronto, ON , Canada 1 University Health Network - Toronto Rehabilitation 2 Institute of Biomaterials and Biomedical Engineering, University of Toronto , Toronto, ON , Canada 3 Rehabilitation Sciences Institute, University of Toronto , Toronto, ON , Canada 4 Institute , Toronto, ON , Canada 5 Department of Occupational Science and Occupational Therapy, University of Toronto , Toronto, ON , Canada 6 Rehabilitation Sciences Institute, Department of Speech-Language Pathology, University of Toronto , Toronto, ON , Canada Background: The purpose of this study was to derive data from real, recorded, personal emergency response call conversations to help improve the artificial intelligence and decision making capability of a spoken dialogue system in a smart personal emergency response system. The main study objectives were to: develop a model of personal emergency response; determine categories for the model's features; identify and calculate measures from call conversations (verbal ability, conversational structure, timing); and examine conversational patterns and relationships between measures and model features applicable for improving the system's ability to automatically identify call model categories and predict a target response. Methods: This study was exploratory and used mixed methods. Personal emergency response calls were preclassified according to call model categories identified qualitatively from response call transcripts. The relationships between six verbal ability measures, three conversational structure measures, two timing measures and three independent factors: caller type, risk level, and speaker type, were examined statistically. Results: Emergency medical response services were the preferred response for the majority of medium and high risk calls for both caller types. Older adult callers mainly requested non-emergency medical service responders during medium risk situations. By measuring the number of spoken words-per-minute and turn-length-in-words for the first spoken utterance of a call, older adult and care provider callers could be identified with moderate accuracy. Average call taker response time was calculated using the number-of-speaker-turns and time-in-seconds measures. Care providers and older adults used different conversational strategies when responding to call takers. The words 'ambulance' and 'paramedic' may hold different latent connotations for different callers. Conclusions: The data derived from the real personal emergency response recordings may help a spoken dialogue system classify incoming calls by caller type with moderate probability shortly after the initial caller utterance. Knowing the caller type, the target response for the call may be predicted with some degree of probability and the output dialogue could be tailored to this caller type. The average call taker response time measured from real calls may be used to limit the conversation length in a spoken dialogue system before defaulting to a live call taker. Personal emergency response system; Conversation analysis; Artificial intelligence; Communication; Aging-in-place; Human-computer interaction; Dialogue planning - Background This study is part of a larger project involving the design and development of a smart home health monitoring system called, the Health Evaluation Logging and Personal Emergency Response (HELPER) system. The HELPER system incorporates automatic fall detection and a spoken dialogue system (SDS) for contacting emergency assistance into a smart home. This system is further described by [1–4]. A prototype SDS for personal emergency response (PER) was successfully developed for the HELPER system but the user vocabulary was limited to only two words “yes” or “no” [3, 4]. The HELPER SDS has also only been tested with younger adults in simulated emergency situations. Continuing from this previous work, this study sought to identify data useful for improving the robustness of the SDS prior to field testing with older adult users. During a PER call, a live PER call taker is able to identify the main caller, assess the situation risk, modify on-going dialogue, and determine the desired or appropriate response. The overall goal of this study was to conduct exploratory content analyses on real, transcribed PER call conversations to derive data that could be used to improve a SDS’s ability to artificially mimic the intelligence and decision making capability of a human call taker. Smart homes and personal emergency response systems In recent decades there has been mounting concern over the rising aging population, with associated long term care r (...truncated)


This is a preview of a remote PDF: http://www.jneuroengrehab.com/content/pdf/s12984-016-0207-9.pdf

Victoria Young, Elizabeth Rochon, Alex Mihailidis. Exploratory analysis of real personal emergency response call conversations: considerations for personal emergency response spoken dialogue systems, Journal of NeuroEngineering and Rehabilitation, 2016, pp. 97, 13, DOI: 10.1186/s12984-016-0207-9