Eliciting Users' Attitudes toward Smart Devices

Abstract

This paper presents a study to determine users' attitudes toward smart devices. We conducted a web survey to elicit users' ratings for devices and combinations of tasks and devices; the results of this survey led to the development of a Recommender System (RS ) for smart devices for particular tasks. We investigated user-and item-based Collaborative Filters, and compared their performance with that of global and demographic RS baselines. We then developed a technique based on Principal Components Analysis to select a subset of the original survey questions that supports the prediction of users' ratings for device-task combinations. Our results show that the accuracy of an RS that asks only a small subset of the survey questions is similar to that of an RS that predicts users' answers to one survey question on the basis of their answers to all the other questions.

Exploratory analysis of Sony AIBO users

“…H2 was rejected because elder people did not perceive Sony AIBO as a companion and younger generations were not more interested in the technology side of these robots. This result is similar to [24] in which Australian participants over 50 years disliked the robotic pets, younger Italian generations had more positive feelings towards robots in [26] and Ezer reached the same conclusion in [25] with American citizens, the acceptance was higher among younger adults in pre-adoption phase (without firsthand experience with robots). However, two studies [15,20] found the opposite in the Japanese society.…”

“…The questionnaire was filled by 57 males and 19 females, since two participants did not reveal their gender, with a ratio 73%/24%, similar to the reported 69%/31% gender ratio of AIBO owners in [28] and another on-line AIBO questionnaire with 64%/36% in [1]. Although there was no question about the income and the wealth of the participants, the authors can explain this rate with the possible higher interest of the men in gadgets and they can afford more to buy expensive robots [16,24]. The technical enthusiasm was also reflected in the professions because most owners were engineers, software developers or technicians (27% for Tech in Fig.…”

“…None of the studies in this subsection reviewed actual users of a robot or the effects after extensive interactions thus all participants were before pre-adoption stage. If the questionnaire in this paper can reveal similar tendencies to [1,15,18,19,20,24] then the new results may generalize to the population.…”

“…Zhan et al [24] studied the attitudes towards smart devices with mainly Australian participants to develop a Recommender System for particular tasks. The male participants were more likely to accept robots than the female and the age did not influence their ratings except the robotic pet which was disliked over 50 years of age.…”

Users’ search performance prediction in cross-device search

“…Root mean square error (RMSE) (Zhan et al, 2016) was used to validate these eight models. RMSE can reflect the precision of models.…”