XWiki - Test

= Problem statement and research questions =

People with dementia often forget to eat and drink, leading to dehydration, malnutrition and decreased wellbeing in general. Our prototype engages in discourses to remind PwD to have lunch and drink water, using the Nao robot platform. The discourse aims to reming the PwD without causing any anxiety or embarrassment which a traditional "alarm" system could cause, and keep them company throughout these activities.

4

5

The four research questions studied in this evaluation are:

6

7

1*. Does the robot cause PwD to eat more regularly?

8

2. "Does the robot remind the PwD of their hunger?"

9

3. "Does the music make the eating more enjoyable for the PwD?"

10

4. "Does the PwD experience less negative emotions, such as agitation, sadness, embarrassment, after the interaction with the 'intelligent' robot?"

11

12

* This research question is difficult due to the practical limitations in designing the experimental setup and as such is left to lesser importance.

= Method =

The prototype is evaluated with an in-person experiment with multiple participants. In the experiment, the participants will be asked to pretend to be PwD and act accordingly with/without the prototype.

== Participants ==

As there are practical difficulties with conducting the experiment with actual people with dementia due to both time constraints and COVID, our participants' group will consist of peers from other groups and friends, who will act as if they are older people with dementia. We plan to gather around 20 people for our experiments.

21

22

== Experimental design ==

23

24

We will be using a within-subject design. In the experiment all of the participants will interact with both versions of the robot, with half of the participants interacting with the version 1 first and then version 2, and the other half in reverse order, to counter-balance the carryover effects. Snacks will be made available for the participants, in case they're prompted and they're hungry. The participants will be unaware of the possibility of eating snacks, to prevent disturbing the interaction with the robot. Otherwise the subjects could be primed for eating, which would bias the results and hide the effect of the robotic interaction.

== Tasks ==

The participant will have to interact with the robot, which is programmed to engage in a lunch discourse. Two versions will be implemented: the first version will ask basic questions about mealtime, mostly acting as a reminder for the PwD to have lunch (alarm clock). The second will be our original implementation of it with the more sophisticated discourse and music.

== Measures ==

We plan on measuring the effectiveness of the discourse, both physically and emotionally. Our quantitative measure is whether the person ate the lunch they were supposed to have eaten, and the qualitative measure is the emotions that the PwD experienced before, during, and after the interaction. The qualitative measures will be recorded with a simple questionnaire. Depending on the time of the experiments, we assume that people might also not be hungry enough to be prompted to have something to eat, which might disturb the results. We do plan however to measure whether the robot will remind someone of their hunger and have them eat.

== Procedure ==

* Welcome Participants and explain what they are going to be doing.

37

* Have them sign the permission form.

38

* Participants complete a questionnaire(A) regarding their emotional state (control).

39

* Have version A of interaction with the robot.

40

* Complete questionnaire(extended version).

41

* Have a short interview during downtime (prepared questions).

42

* Have version B of interaction with the robot.

43

* Complete questionnaire(extended version).

44

* Have a short interview during downtime (prepared questions).

== Material ==

For the experiments, we'll be using the NAO robot platform, as well as a laptop for the participants to complete the questionnaires on. The questionnaire will be a combination of questions regarding the emotional state of the participants, their interaction with the robot, and the music included in the interaction. Food will be made available to see and measure how much people will eat.

49

50

Questionnaires:

51

Consent Form and Disclaimers

52

8 questions from the [[EVEA>>https://www.ucm.es/data/cont/docs/39-2013-04-19-EVEA%20-%20Datasheet.pdf]] questionnaire

53

4 questions from the [[Godspeed>>https://www.bartneck.de/2008/03/11/the-godspeed-questionnaire-series/]] questionnaire

54

3 food-related questions of our own (5-point Likert scale)

55

2 music-related questions of our own (5-point Likert scale)

== Practicalities ==

Beforehand:

* Do a practice round by ourselves

62

** Film this

63

* Contact other groups and decide on a time slot

64

** Might be better to reserve in 10 min slots, so that people don't have to wait so much

65

** If possible, this could be done in parallel with another groups testing

* Reserve lab

* Buy snacks

During:

1. Give starting questionnare to fill while people are waiting for the previous participant

72

2. Guide the participant to the testing spot

73

3. Inform the participant where the snacks are

74

4. Run the first version

75

5. Give the mid-questionnare

76

6. Run the other test

77

7. Conduct the questionnare for the participant

78

8. Give the participant the end-questionnare

79

80

Other practicalities during:

81

82

* We will use the "Wizard of Oz" method for recognizing agreement and disagreement, to make sure that the whole process does not depend on voice recegnition being good enough

83

** Someone will press eg. "y" and "n" on the keyboard according to the participants answers

84

* We will change the order in which the smart and basic versions are for each participant

85

** this way if someone doesn't show up, we don't get skewed amounts

After:

* Analyze results

= Results =

The results were gathered from 19 personnel, all of whom interacted first with one version of the robot and then the other. 10 of the participants interacted first with the simple version, nine having their first interaction with the advanced version.

== Eating ==

(% style="text-align:center" %)

102

Figure 1: Results on the eating of the test personas during the experiment

Simple robot:

* 16% ate

* 33% of those would not have eaten without the robot

Advanced robot:

* 32% ate

* 67% of those would not have eaten without the robot

== Music ==

(% style="text-align:center" %)

121

Figure 2: Answers of the test personas regarding music

== EVEA (Mood) ==

(% style="text-align:center" %)

131

Figure 3: Median measured moods for the simple version of the robot

(% style="text-align:center" %)

138

Figure 4: Median measured moods for the advanced version of the robot

139

140

(% style="text-align:center" %)

141

Table 1: Wilcoxon signed rank test results for the hypothesis that the mood changed during the interaction with the simple robot

|Statistic|37|5|4|14

|P-value|0.54|0.01|0.01|0.45

146

147

(% style="text-align:center" %)

148

Table 2: Wilcoxon signed rank test results for the null hypothesis that the mood changed during the interaction with the advanced robot

149

150

151

|Statistic|32|11|2|17

152

|P-value|0.18|0.01|0.01|0.45

153

154

(% style="text-align:center" %)

155

Table 3: Wilcoxon signed rank test results for the null hypothesis that the mood decreased during the interaction with the simple robot

156

157

|=Mood|=Anxiety|=Sadness|=Anger

158

|Statistic|81|53|29

159

|P-value|0.01|0.00|0.23

160

161

(% style="text-align:center" %)

162

Table 4: Wilcoxon signed rank test results for the null hypothesis that the mood decreased during the interaction with the advanced robot

163

164

|=Mood|=Anxiety|=Sadness|=Anger

165

|Statistic|32|149|52

166

|P-value|0.00|0.01|0.07

167

168

(% style="text-align:center" %)

169

Table 5: Wilcoxon signed rank test results for the null hypothesis that the mood increased during the interaction with the simple robot

|=Mood|=Happiness

|Statistic|37

|P-value|0.27

(% style="text-align:center" %)

176

Table 6: Wilcoxon signed rank test results for the null hypothesis that the mood increased during the interaction with the advanced robot

|=Mood|=Happiness

|Statistic|32

|P-value|0.09

(% style="text-align:center" %)

183

Table 7: Wilcoxon signed rank test results for the hypothesis that the mood changes with the simple and advanced robots during the interaction are different

184

185

186

|Statistic|92|49|85|69

187

|P-value|0.92|0.07|0.71|0.31

== Godspeed ==

(% style="text-align:center" %)

196

Figure 5: Answers to the statement 'I thought the robot was friendly'

(% style="text-align:center" %)

203

Figure 6: Answers to the statement 'I thought the robot was pleasant'

(% style="text-align:center" %)

210

Figure 7: Median measured Godspeed questionnaire dimensions

211

212

213

(% style="text-align:center" %)

214

Table 8: Wilcoxon signed rank test results for the null hypothesis that the advanced robot scored higher in the perceived dimensions

215

216

|=Dimension|=Likeability|=Intelligence

|Statistic|36|70

|P-value|0.01|0.17

= Discussion =

Analysis the results surfaced some minor issues in the experiment, such as the lack of comparison with two robots of similar features, with and without music. Also the practical limitations in the setup, such as the lack of different food options and some participants being aware of the design goals of the prototype could have interfered with the natural flow of the intercourse. With these limitations, the research method was successful in extracting differences within the robots and brought up additional directions for future research.

222

223

The most interesting direction for future research would be the longer term studying of the effect of mealtime reminders on the health of the test subjects. The longer term health study would uncover the effect on eating frequency and the development of the relationship with the robot, for example would the test subjects that were first excited about the novel interaction with the robot, develop negative feelings about the supervision that the robot is conducting into their personal life.

224

225

Another topic to study is the differences with and without music. The effects of music could be studied with the music tailored to personal taste and all versions of the robot with and without the music playback included in the interaction. This would allow to pinpoint the effects of music, without the other features causing variance.

= Conclusions =

From the results we can see that the more advanced robot shows advantages over the simple version in many categories. Hints of better performance in other categories can be seen, but no conclusions should be drawn from the ones that lack the statistical significance.

230

231

In improving the eating, it seems that both robots have limited success in causing the people to eat as seen in Figure 1, they could cause the patients to eat more regularly, if triggered by timers or other suitable systems. It also seems that the advanced robot is better in the reminding, by a slight margin. However, the long term effects of reminding should be researched more to conclude whether the usage of the demonstrated robot platform or similar would cause the patients to eat more regularly. It is also unclear how the test setup and the limited choice of food affected the eating.

232

233

Based on the answers of the participants regarding music seen in Figure 2, it seems that most of them were either indifferent or liked the music. Also, as the test personnel find the advanced robot more likeable with a 5% confidence limit (Table 7), and the advanced version was the only version with music, it seems likely that the music does make the interaction more pleasant for the personas. However, some of the likeability might be due to the other advanced features of the robot and thus more research is needed to conclude the effect of the music.

234

235

The EVEA and partial Godspeed result can be seen in Figures 3-7 and Tables 1-8. The results show that with reasonable confidence (5% confidence limit), both versions of the robot decreased sadness and anxiety in the test personas. Hints are shown (10% confidence limit) that the advanced robot also decreases feelings of anger and increases happiness, while the simple robot fails to show similar results. However, in Table 7 we can see that the statistical differences in the mood differences during the interactions with the different versions are not highly significant.

236

237

A Wilcoxon signed rank test for the partial Godspeed test shows in Table 8 that with high confidence (1% confidence limit), the intelligent robot is more likeable in comparison to the simple robot. With these results it is likely that the more advanced robot is slightly preferrable and the personas might experience less negative emotions after the interaction with the robots, but it is slightly unclear if the effect is more powerful with the advanced robot.

= Appendix =

== Experiment introduction for participants ==

Hi, we are <NAME> and <NAME> from the TU Delft Socio-Cognitive Engeering course Group 1, thank you for participating in our prototype evaluation experiment. The experiment is being conducted as a part of the TU Delft course on Socio-Cognitive Engineering and aims to evaluate the prototype designed as a part of the course. The evaluated prototype is based on the Nao robot-platform and is intended to improve the wellbeing of people suffering of dementia.

247

248

Consuming food and/or water can be a consequence of the interaction between you and the robot. Therefore, we would like to ask you if you have any allergies. If you have a form of Diabetes, please let us know before we start the first part of the experiment. You are strongly encouraged to share any other health conditions that can possibly be relevant to take into account when doing an experiment with robots and food with us.

249

250

The link between the stimuli of the Nao-robot and the triggering of epileptic seizures is yet unknown. If you have ever experienced epileptic seizures, please let us know. Then, we could see if any special precautions are needed.

251

252

The experiment will last for approximately 15-20 minutes, and consists of two interaction sections with the Nao robot, as well as questionnaires before, between and after the sections. We kindly ask you to act naturally during the experiment and fill the questionnaires truthfully and intuitively. Remember that we are evaluating the prototypes performance, not yours. You can stop the experiment at any time.

253

254

We will be collecting data of the questionnaires and recording some experiments, do you agree with your experiment being recorded? All data excluding the recordings will be anonymised before analysis and storage. The recordings will not be shared with third parties. After the experiment you have the right to ask for information about the collected data and revoke the right to use it. We kindly ask you not to share any information about the experiment with other participants.

255

 Do you have any questions?

256

257

== After research interview ==

258

259

Setup:

260

The test subject has finished both parts of the experiment. Before leaving the test conductor(s) sit down with them and ask the following questions in a discussion about the experiment. Discussion can flow freely, but the following topics should be discussed.

261

262

Topics:

263

- Emotions before / during / after the interaction with the robot

264

- Agitation due to the robot suggesting eating

265

- Effect of music on the general feeling of the situation

266

- Feeling of company during eating

267