Wiki source code of Test

Version 86.1 by Aleksanteri Hämäläinen on 2022/04/03 17:59

version	line-number	content
2.1	1	= Problem statement and research questions =
1.1	2
9.1	3	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.
1.1	4
73.1	5	The four research questions studied in this evaluation are:
3.1	6
77.1	7	{{html}}
74.1	8
78.1	9	<ol>
79.1	10	<li>Does the robot remind the PwD of their hunger?</li>
	11	<li>Does the music make the eating more enjoyable for the PwD?</li>
	12	<li>Does the PwD experience less negative emotions, such as agitation, sadness, embarrassment, after the interaction with the 'intelligent' robot?</li>
84.1	13	<li>* Does the robot cause PwD to eat more regularly?</li>
78.1	14	</ol>
77.1	15
83.1	16	* This research question is difficult due to the practical limitations in designing the experimental setup and as such is left to lesser importance.
	17
77.1	18	{{/html}}
	19
2.1	20	= Method =
1.1	21
86.1	22	The prototype is evaluated with an in-person experiment with multiple participants.
1.1	23
2.1	24	== Participants ==
1.1	25
86.1	26	As there are practical difficulties with conducting the experiment with actual people with dementia due to both time constraints and COVID, our participants' group consists of peers from other groups and friends. In total we had 19 people take part in our experiment.
1.1	27
2.1	28	== Experimental design ==
1.1	29
86.1	30	For the experiment we used a within-subject design. All of the participants interacted 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. This was done to counter-balance the carryover effects. Snacks were made available for the participants, in case they were prompted and they ewre hungry. The participants were unaware of the possibility of eating snacks, to prevent disturbing the interaction with the robot. Otherwise the subjects would have been primed for eating, which would have biased the results and hide the effect of the robotic interaction.
1.1	31
2.1	32	== Tasks ==
1.1	33
86.1	34	The participant interacted with the robot, which was programmed to engage in a lunch discourse. Two versions were implemented: the first version asks basic questions about mealtime, mostly acting as a reminder for the PwD to have lunch (basically an alarm clock). The second is our original implementation of it with the more sophisticated discourse and music.
1.1	35
2.1	36	== Measures ==
1.1	37
86.1	38	We measured the effectiveness of the discourse, both physically and emotionally. Our quantitative measure was whether the person ate the lunch they were supposed to have eaten, and the qualitative measure was the emotions that the PwD experienced before, during, and after the interaction. The qualitative measures were recorded with a simple questionnaire. Some people were not hungry enough to be prompted to have something to eat, which disturbed the results. However we did measure whether the robot reminded someone of their hunger and if they ate.
1.1	39
2.1	40	== Procedure ==
1.1	41
86.1	42	The procedure was conducted as follows:
	43
	44	1. Welcome participant and explain what they are going to be doing.
	45	2. Have them sign the permission form.
	46	* Complete questionnaire 1 regarding their emotional state (control).
	47	* Have an interaction with version A of the robot.
	48	* Complete questionnaire 2 (extended version).
4.1	49	* Have a short interview during downtime (prepared questions).
86.1	50	* Have an interaction with version B of the robot.
	51	* Complete questionnaire 3 (extended version).
4.1	52	* Have a short interview during downtime (prepared questions).
1.1	53
2.1	54	== Material ==
1.1	55
9.1	56	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.
1.1	57
20.1	58	Questionnaires:
	59	Consent Form and Disclaimers
	60	8 questions from the [[EVEA>>https://www.ucm.es/data/cont/docs/39-2013-04-19-EVEA%20-%20Datasheet.pdf]] questionnaire
	61	4 questions from the [[Godspeed>>https://www.bartneck.de/2008/03/11/the-godspeed-questionnaire-series/]] questionnaire
	62	3 food-related questions of our own (5-point Likert scale)
	63	2 music-related questions of our own (5-point Likert scale)
	64
11.1	65	== Practicalities ==
1.1	66
11.1	67	Beforehand:
17.1	68
11.1	69	* Do a practice round by ourselves
	70	** Film this
	71	* Contact other groups and decide on a time slot
	72	** Might be better to reserve in 10 min slots, so that people don't have to wait so much
	73	** If possible, this could be done in parallel with another groups testing
	74	* Reserve lab
	75	* Buy snacks
	76
	77	During:
17.1	78
11.1	79	1. Give starting questionnare to fill while people are waiting for the previous participant
	80	2. Guide the participant to the testing spot
	81	3. Inform the participant where the snacks are
	82	4. Run the first version
	83	5. Give the mid-questionnare
	84	6. Run the other test
13.1	85	7. Conduct the questionnare for the participant
	86	8. Give the participant the end-questionnare
11.1	87
17.1	88	Other practicalities during:
11.1	89
	90	* 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
	91	** Someone will press eg. "y" and "n" on the keyboard according to the participants answers
	92	* We will change the order in which the smart and basic versions are for each participant
	93	** this way if someone doesn't show up, we don't get skewed amounts
	94
	95	After:
17.1	96
11.1	97	* Analyze results
	98
35.1	99	= Results =
1.1	100
58.1	101	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.
	102
41.1	103	== Eating ==
	104
	105	{{html}}
44.1	106	<img src="https://xwiki.ewi.tudelft.nl/xwiki/wiki/sce2022group01/download/Test/WebHome/EatingComp.png?rev=1.1" alt="Results on the eating of the test personas" style="display:block;margin-left:auto;margin-right:auto" width=750/>
41.1	107	{{/html}}
	108
	109	(% style="text-align:center" %)
62.1	110	Figure 1: Results on the eating of the test personas during the experiment
41.1	111
59.1	112	Simple robot:
	113
	114	* 16% ate
	115	* 33% of those would not have eaten without the robot
	116
	117	Advanced robot:
	118
	119	* 32% ate
	120	* 67% of those would not have eaten without the robot
	121
66.1	122	== Music ==
	123
	124	{{html}}
	125	<img src="https://xwiki.ewi.tudelft.nl/xwiki/wiki/sce2022group01/download/Test/WebHome/MusicEnjoyable.png?rev=1.1" alt="Effects of music on the test personnel" style="display:block;margin-left:auto;margin-right:auto" width=1250/>
	126	{{/html}}
	127
	128	(% style="text-align:center" %)
67.1	129	Figure 2: Answers of the test personas regarding music
66.1	130
	131
51.1	132	== EVEA (Mood) ==
29.1	133
	134	{{html}}
45.1	135	<img src="https://xwiki.ewi.tudelft.nl/xwiki/wiki/sce2022group01/download/Test/WebHome/MoodChangeDumb.png?rev=1.1" alt="Measured moods and changes for the simple robot" style="display:block;margin-left:auto;margin-right:auto" width=750/>
29.1	136	{{/html}}
	137
32.2	138	(% style="text-align:center" %)
67.1	139	Figure 3: Median measured moods for the simple version of the robot
30.1	140
32.2	141	{{html}}
45.1	142	<img src="https://xwiki.ewi.tudelft.nl/xwiki/wiki/sce2022group01/download/Test/WebHome/MoodChangeSmart.png?rev=1.1" alt="Measured moods and changes for the advanced version of the robot" style="display:block;margin-left:auto;margin-right:auto" width=750/>
32.2	143	{{/html}}
	144
	145	(% style="text-align:center" %)
67.1	146	Figure 4: Median measured moods for the advanced version of the robot
29.1	147
33.1	148	(% style="text-align:center" %)
62.1	149	Table 1: Wilcoxon signed rank test results for the hypothesis that the mood changed during the interaction with the simple robot
37.1	150
	151	\|=Mood\|=Happiness\|=Anxiety\|=Sadness\|=Anger
	152	\|Statistic\|37\|5\|4\|14
	153	\|P-value\|0.54\|0.01\|0.01\|0.45
	154
	155	(% style="text-align:center" %)
62.1	156	Table 2: Wilcoxon signed rank test results for the null hypothesis that the mood changed during the interaction with the advanced robot
37.1	157
	158	\|=Mood\|=Happiness\|=Anxiety\|=Sadness\|=Anger
49.1	159	\|Statistic\|32\|11\|2\|17
	160	\|P-value\|0.18\|0.01\|0.01\|0.45
37.1	161
	162	(% style="text-align:center" %)
62.1	163	Table 3: Wilcoxon signed rank test results for the null hypothesis that the mood decreased during the interaction with the simple robot
33.1	164
35.1	165	\|=Mood\|=Anxiety\|=Sadness\|=Anger
	166	\|Statistic\|81\|53\|29
38.1	167	\|P-value\|0.01\|0.00\|0.23
33.1	168
34.1	169	(% style="text-align:center" %)
62.1	170	Table 4: Wilcoxon signed rank test results for the null hypothesis that the mood decreased during the interaction with the advanced robot
33.1	171
35.1	172	\|=Mood\|=Anxiety\|=Sadness\|=Anger
36.1	173	\|Statistic\|32\|149\|52
38.1	174	\|P-value\|0.00\|0.01\|0.07
34.1	175
35.1	176	(% style="text-align:center" %)
62.1	177	Table 5: Wilcoxon signed rank test results for the null hypothesis that the mood increased during the interaction with the simple robot
34.1	178
35.1	179	\|=Mood\|=Happiness
	180	\|Statistic\|37
38.1	181	\|P-value\|0.27
35.1	182
	183	(% style="text-align:center" %)
62.1	184	Table 6: Wilcoxon signed rank test results for the null hypothesis that the mood increased during the interaction with the advanced robot
35.1	185
	186	\|=Mood\|=Happiness
	187	\|Statistic\|32
38.1	188	\|P-value\|0.09
35.1	189
69.2	190	(% style="text-align:center" %)
	191	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
	192
	193	\|=Mood\|=Happiness\|=Anxiety\|=Sadness\|=Anger
	194	\|Statistic\|92\|49\|85\|69
	195	\|P-value\|0.92\|0.07\|0.71\|0.31
	196
52.1	197	== Godspeed ==
	198
40.1	199	{{html}}
46.1	200	<img src="https://xwiki.ewi.tudelft.nl/xwiki/wiki/sce2022group01/download/Test/WebHome/friendly-hist.png?rev=1.1" alt="Effects of music on the test personnel" style="display:block;margin-left:auto;margin-right:auto" width=750/>
41.1	201	{{/html}}
40.1	202
41.1	203	(% style="text-align:center" %)
62.1	204	Figure 5: Answers to the statement 'I thought the robot was friendly'
41.1	205
40.1	206	{{html}}
46.1	207	<img src="https://xwiki.ewi.tudelft.nl/xwiki/wiki/sce2022group01/download/Test/WebHome/pleasant-hist.png?rev=1.1" alt="Answers to the statement 'I thought the robot was pleasant'." style="display:block;margin-left:auto;margin-right:auto" width=750/>
40.1	208	{{/html}}
	209
	210	(% style="text-align:center" %)
62.1	211	Figure 6: Answers to the statement 'I thought the robot was pleasant'
40.1	212
54.1	213	{{html}}
	214	<img src="https://xwiki.ewi.tudelft.nl/xwiki/wiki/sce2022group01/download/Test/WebHome/godspeed-barchart.png?rev=1.1" alt="Godspeed questionnaire median comparison'." style="display:block;margin-left:auto;margin-right:auto" width=750/>
	215	{{/html}}
1.1	216
54.1	217	(% style="text-align:center" %)
62.1	218	Figure 7: Median measured Godspeed questionnaire dimensions
41.1	219
64.1	220
	221	(% style="text-align:center" %)
71.1	222	Table 8: Wilcoxon signed rank test results for the null hypothesis that the advanced robot scored higher in the perceived dimensions
64.1	223
56.1	224	\|=Dimension\|=Likeability\|=Intelligence
55.1	225	\|Statistic\|36\|70
	226	\|P-value\|0.01\|0.17
52.1	227
72.1	228	= Discussion =
	229	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.
	230
	231	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.
	232
	233	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.
	234
57.1	235	= Conclusions =
54.1	236
62.2	237	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.
54.1	238
64.2	239	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.
55.1	240
68.1	241	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.
64.2	242
71.1	243	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.
64.2	244
71.1	245	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.
68.1	246
	247
10.1	248	= Appendix =
	249
17.1	250	== Experiment introduction for participants ==
16.1	251
17.1	252
16.1	253
17.1	254	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.
16.1	255
19.1	256	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.
	257
	258	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.
	259
18.1	260	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.
17.1	261
	262	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.
16.1	263	Do you have any questions?
	264
10.1	265	== After research interview ==
	266
	267	Setup:
	268	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.
	269
	270	Topics:
	271	- Emotions before / during / after the interaction with the robot
	272	- Agitation due to the robot suggesting eating
	273	- Effect of music on the general feeling of the situation
	274	- Feeling of company during eating
	275	- Effectiveness of eating/drinking suggestions
	276
12.1	277	Questions:
	278	- Did you eat or drink anything during the experiment?
	279	- Were you feeling hungry/thirsty beforehand and did the discourse change this?
	280	- On a scale of 1-10, how likely would you have eaten/drank without the robot suggesting it?
10.1	281	- What did the interaction with the robot feel like?
	282	- With the more intelligent version?
	283	- With the less intelligent version?
	284	- What did you feel like when the robot suggested you should eat/drink?