Conversational Frames: Improving Conversation Context in Smart Personal Assistants

Conversational Frames: Improving Conversation Context in Smart Personal Assistants

Omar Saad Almousa (Jordan University of Science and Technology, Jordan), Hazem Migdady (Oman College of Management and Technology, Muscat, Oman) and Mohammad Al-Talib (Yarmouk University, Jordan)
DOI: 10.4018/IJERTCS.2020100106
OnDemand PDF Download:
No Current Special Offers


This paper extends the previous work of Almousa and Migdady by proposing and implementing three models to improve the correctness and naturality of the given answers of smart personal assistants (SPAs). The motivation behind the three proposed models is the failure of some well-known existing SPAs (Siri and Salma) to extract contextual information from a conversation. The authors call this kind of information: the conversational frame. For evaluating the suggested models, the authors also implement an abstraction of the existing SPAs that they call non-framed model. To evaluate the four implementations, 36 respondents answered an on-line questionnaire after watching four videos that the authors recorded per implementation. The authors statistically prove that their three suggested models precede the non-framed model. The researchers attribute this to the fact that our models overcome the shortcoming present in non-framed model. Moreover, their model that implements the conversational frame precedes all other models.
Article Preview

1. Introduction

Smart Personal Assistant (SPA) is a human-machine application that helps its user by meeting her requests such as answering questions, providing suggestions, and performing certain activities (Tulshan & Dhage, 2018). Along this paper, the term SPA is used to abstract many literature terms like Intelligent Personal Assistant, Virtual Personal Assistant, Personal Digital Assistants, and Conversational Agent, to name a few. The prototype of Smart Personal Assistants (SPAs) as we know today was introduced by IBM Simon 1994 (iPhone 4S hands-on! — Engadget, 2011). After almost two decades, Apple presented its first iPhone 4s-based SPA as a novel feature (Siri - Apple, 2020). An overview of Siri was presented by (Shakeel, Tabasum, & Ahmad, 2017) as an SPA to explain the evolution in the interaction between human and machine. They stated mainly three features that any SPA should satisfy: 1) Simplicity 2) Flexibility and 3) Easiness of Interaction. Asserting that the easiest interaction is the voice-based communication since it satisfies two of the three former features, in particular: simplicity and flexibility in addition to the fact that it does not critically depend on any cognitive efforts.

However, the usage of SPAs still hold some restrictions, such as: 1) the complexity-level in the speech of the human and 2) the varying of context form. This actually interprets the specific description usage of all available SPAs until now. Anyhow, the industry of SPAs did not slow down, actually the industry grown dramatically and a number of new SPAs were introduced into the market. Despite the increasing number of available SPAs in the market nowadays, there are four popular SPAs: Cortana of Microsoft, Siri of Apple, Google Assistant, and Alexa of Amazon.

Madalli, et. al., (2018) presented a review on using voice-based smart personal assistants as a technique to reduce the gap of communication and interaction between real and physical worlds. For instance, Siri of Apple applies the techniques of deep learning in order to detect user activities, and hence it can introduce personalized recommendations. Zue et al., (2000) believe that machine learning along with AI approaches has many areas to be thrust in, such as fields of cognitive and learning, games design, psychology, etc. A giant evolution is in progress nowadays in the market of SPAs. This could be expressed efficiently when the value of an IPA is presented money wise. Chung et. al. (2016) mentioned that a threshold of $2 billion will be exceeded by 2020 by the industry of the SPAs (Worldwide Spending on VPA-Enabled Wireless Speakers Will Top $2 Billion by 2020, 2016). Which emphasizes the importance and the volume of such industry in the field of modern technology. Moreover, (Cowan et al., 2017) and (Intelligent Personal Assistant - KAMITIS, 2016) provided a very optimistic study about the share of the SPAs in the market, since, in less than a year from now, that share may reach the point of $4.6 billion. In addition (The Virtual Digital Assistant Market— Tractica, 2016) mentioned dependency of the people on the SPAs worldwide in the coming future, and found that the number of users of such technology may reach 1.8 billion by the end of 2020. Actually, this forms an increment with more than $1.4 billion in comparison with the number of users in 2015.

Complete Article List

Search this Journal:
Open Access Articles
Volume 13: 4 Issues (2022): 1 Released, 3 Forthcoming
Volume 12: 4 Issues (2021)
Volume 11: 4 Issues (2020)
Volume 10: 4 Issues (2019)
Volume 9: 2 Issues (2018)
Volume 8: 2 Issues (2017)
Volume 7: 2 Issues (2016)
Volume 6: 2 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing