WEBVTT

1
00:00:00.120 --> 00:00:02.439
<v Speaker 1>Welcome to the deep dive. We're here to help you

2
00:00:02.439 --> 00:00:04.639
<v Speaker 1>get the essential knowledge from sources.

3
00:00:04.440 --> 00:00:06.320
<v Speaker 2>Fast yep, straight to the good stuff.

4
00:00:06.360 --> 00:00:10.759
<v Speaker 1>Today, we're plunging into a really interesting space where software

5
00:00:10.800 --> 00:00:14.720
<v Speaker 1>engineering meets games. But you know, not just for fun.

6
00:00:14.800 --> 00:00:17.239
<v Speaker 1>We're talking serious applications.

7
00:00:16.559 --> 00:00:21.760
<v Speaker 2>Exactly, think education, training, maybe tackling real world problems. It's

8
00:00:21.800 --> 00:00:23.120
<v Speaker 2>about more than high scores.

9
00:00:23.640 --> 00:00:26.640
<v Speaker 1>So if you're listening, you're probably looking for a let's say,

10
00:00:26.839 --> 00:00:29.640
<v Speaker 1>quick but solid grasp of this, trying to get those

11
00:00:29.879 --> 00:00:32.719
<v Speaker 1>aha moments without wading through tons of jargon.

12
00:00:32.799 --> 00:00:34.960
<v Speaker 2>That's the idea and our main guide here is the

13
00:00:35.000 --> 00:00:39.560
<v Speaker 2>book Software Engineering for Games in Serious Contests Theories, Methods,

14
00:00:39.640 --> 00:00:43.200
<v Speaker 2>tools and Experiences. It's edited by Kendrick Cooper and Antonio

15
00:00:43.280 --> 00:00:43.840
<v Speaker 2>Book your Own.

16
00:00:44.079 --> 00:00:46.840
<v Speaker 1>And what's really impressive, I think is the sheer range

17
00:00:46.840 --> 00:00:48.799
<v Speaker 1>of voices in this book. It's not just one or

18
00:00:48.799 --> 00:00:50.240
<v Speaker 1>two perspectives.

19
00:00:49.719 --> 00:00:52.479
<v Speaker 2>No, not at all. We're talking forty five authors from

20
00:00:52.560 --> 00:00:53.640
<v Speaker 2>nine different countries.

21
00:00:53.880 --> 00:00:56.679
<v Speaker 1>Wow. So that gives you a really broad view right

22
00:00:56.719 --> 00:01:00.359
<v Speaker 1>on how game design ideas and solid software practices are

23
00:01:00.920 --> 00:01:03.159
<v Speaker 1>well coming together in some quite important ways.

24
00:01:03.240 --> 00:01:04.439
<v Speaker 2>Yeah, a really rich picture.

25
00:01:04.560 --> 00:01:06.719
<v Speaker 1>So our mission today is basically to dig into the

26
00:01:06.719 --> 00:01:10.799
<v Speaker 1>core concepts, understand the challenges, you know, in using software

27
00:01:10.840 --> 00:01:13.959
<v Speaker 1>engineering to build serious games that actually work and keep

28
00:01:14.000 --> 00:01:14.560
<v Speaker 1>people hooked.

29
00:01:14.599 --> 00:01:18.799
<v Speaker 2>Okay, sounds good. Where should we start maybe with just

30
00:01:18.840 --> 00:01:20.480
<v Speaker 2>how complex these things are to.

31
00:01:20.480 --> 00:01:23.200
<v Speaker 1>Build good idea? Yeah, because it's not just coding, is it.

32
00:01:23.200 --> 00:01:25.560
<v Speaker 1>It's inherently interdisciplinary.

33
00:01:24.799 --> 00:01:27.319
<v Speaker 2>Absolutely not just coding. The book really lays it out.

34
00:01:27.359 --> 00:01:32.599
<v Speaker 2>You've got inputs from well, the arts, behavioral sciences, business, education,

35
00:01:32.760 --> 00:01:36.359
<v Speaker 2>engineering itself, humanities, even physical sciences.

36
00:01:35.840 --> 00:01:38.560
<v Speaker 1>And math, and then domain specific stuff like healthcare too.

37
00:01:38.799 --> 00:01:41.040
<v Speaker 2>It's a real mix, and it's worth thinking about what

38
00:01:41.120 --> 00:01:44.200
<v Speaker 2>each brings. Like the arts give you the visuals, the sound,

39
00:01:44.280 --> 00:01:47.519
<v Speaker 2>the feel right two D, three D assets, music, even

40
00:01:47.560 --> 00:01:49.439
<v Speaker 2>performance informs, animation, and the.

41
00:01:49.439 --> 00:01:53.480
<v Speaker 1>Humanities that brings in things like ethics, game addiction maybe

42
00:01:53.680 --> 00:01:57.519
<v Speaker 1>or storytelling from literature, you know, crafting the narrative of

43
00:01:57.519 --> 00:01:58.000
<v Speaker 1>the setting.

44
00:01:58.079 --> 00:02:02.560
<v Speaker 2>The behavioral sciences are huge. Anthropology helps with understanding social norms,

45
00:02:02.959 --> 00:02:07.480
<v Speaker 2>communication theory for getting the message across, sociology for multiplayer.

46
00:02:06.959 --> 00:02:11.719
<v Speaker 1>Stuff, and psychology for engagement motivation, how rewards work the

47
00:02:11.759 --> 00:02:13.120
<v Speaker 1>whole gameplay experience.

48
00:02:13.159 --> 00:02:16.879
<v Speaker 2>Really exactly. It underlines that building a good serious game

49
00:02:17.120 --> 00:02:21.319
<v Speaker 2>rests on this incredibly diverse base of knowledge, which.

50
00:02:21.240 --> 00:02:24.599
<v Speaker 1>You know, must make collaboration tricky sometimes compared to more

51
00:02:24.599 --> 00:02:27.400
<v Speaker 1>traditional software projects. You need different ways to talk to

52
00:02:27.479 --> 00:02:27.840
<v Speaker 1>each other.

53
00:02:28.000 --> 00:02:31.960
<v Speaker 2>Yeah, communication is key and connecting it back. This complexity

54
00:02:32.039 --> 00:02:35.919
<v Speaker 2>shows why having strong software engineering practices underneath it all

55
00:02:36.039 --> 00:02:38.080
<v Speaker 2>is so vital. You're juggling so much.

56
00:02:38.439 --> 00:02:43.520
<v Speaker 1>Okay, so complex landscape check. But the influence of games

57
00:02:43.560 --> 00:02:46.800
<v Speaker 1>goes beyond just making serious apps look like games, doesn't it.

58
00:02:46.879 --> 00:02:50.719
<v Speaker 2>Oh definitely. The book talks about game full engineering and gamification,

59
00:02:51.159 --> 00:02:53.599
<v Speaker 2>but applied within software engineering itself.

60
00:02:53.759 --> 00:02:56.120
<v Speaker 1>Right. I saw that table table one point one. It

61
00:02:56.199 --> 00:03:01.719
<v Speaker 1>lists areas like requirements engineering, architecture testing, even project management

62
00:03:01.759 --> 00:03:03.000
<v Speaker 1>and QA getting gamified.

63
00:03:03.199 --> 00:03:05.520
<v Speaker 2>It's kind of surprising, isn't it, seeing these, you know,

64
00:03:05.680 --> 00:03:08.879
<v Speaker 2>seemingly fun techniques popping up in the core processes of

65
00:03:08.919 --> 00:03:09.719
<v Speaker 2>building software.

66
00:03:09.840 --> 00:03:10.599
<v Speaker 1>Yeah, really is.

67
00:03:10.960 --> 00:03:15.360
<v Speaker 2>And there's this idea of directly transferring strategies. Chapter Sun

68
00:03:15.560 --> 00:03:18.960
<v Speaker 2>by Vanisawanik and her colleagues digs into this. They look

69
00:03:18.960 --> 00:03:22.080
<v Speaker 2>at it from three angles. Yeah, player agency giving players

70
00:03:22.159 --> 00:03:27.280
<v Speaker 2>meaningful choices. Then there's serious game modification or modding, and

71
00:03:27.479 --> 00:03:31.879
<v Speaker 2>also the role of AI emotion modeling to design better games.

72
00:03:32.120 --> 00:03:35.360
<v Speaker 1>Interesting. So the stuff that makes regular games fun and

73
00:03:35.400 --> 00:03:38.840
<v Speaker 1>Sticky isn't just for entertainment anymore. It's being used strategically,

74
00:03:38.960 --> 00:03:41.759
<v Speaker 1>even behind the scenes in software.

75
00:03:41.360 --> 00:03:44.840
<v Speaker 2>Creation, which naturally leads to the question, how do we

76
00:03:45.000 --> 00:03:48.680
<v Speaker 2>know if these serious games are actually well working? How

77
00:03:48.680 --> 00:03:51.159
<v Speaker 2>do you measure the user experience effectively?

78
00:03:51.319 --> 00:03:54.719
<v Speaker 1>Ah good transition that brings us to chapter two by

79
00:03:54.800 --> 00:03:57.960
<v Speaker 1>soteririst kre Genus. He points out that game ux depends

80
00:03:58.000 --> 00:03:58.520
<v Speaker 1>on things.

81
00:03:58.360 --> 00:04:01.719
<v Speaker 2>Like flow, that feeling of being totally absorbed.

82
00:04:01.240 --> 00:04:04.080
<v Speaker 1>Right, an immersion, maybe frustration or tension with the right

83
00:04:04.120 --> 00:04:06.879
<v Speaker 1>amount of psychological absorption, and even the social setting.

84
00:04:06.919 --> 00:04:10.199
<v Speaker 2>And there's this breakdown by Roto into three phases of experience,

85
00:04:10.719 --> 00:04:13.800
<v Speaker 2>what you expect beforehand, what happens during play, and the

86
00:04:13.840 --> 00:04:16.680
<v Speaker 2>overall feeling after and he argues.

87
00:04:16.720 --> 00:04:20.480
<v Speaker 1>The during interaction part is the most crucial for making improvements.

88
00:04:20.000 --> 00:04:22.920
<v Speaker 2>Right exactly, And then Lalaman adds more detail to that

89
00:04:23.040 --> 00:04:26.199
<v Speaker 2>during phase. He says it's influenced by the person playing,

90
00:04:26.240 --> 00:04:28.279
<v Speaker 2>their mood, motivation.

91
00:04:28.199 --> 00:04:30.480
<v Speaker 1>Needs, okay, the human factor.

92
00:04:30.240 --> 00:04:35.279
<v Speaker 2>Yep, then the system itself, it's complexity, purpose, usability, and

93
00:04:35.360 --> 00:04:39.240
<v Speaker 2>finally the context of the environment, whether it feels meaningful voluntary.

94
00:04:39.920 --> 00:04:42.600
<v Speaker 1>So loads of factors how do they suggest evaluating all this,

95
00:04:42.959 --> 00:04:45.160
<v Speaker 1>especially if you want quick and thorough insights.

96
00:04:45.399 --> 00:04:48.959
<v Speaker 2>Well, the book covers several methods. There's expert evaluation, basically

97
00:04:49.360 --> 00:04:53.480
<v Speaker 2>getting designers or ux pros to give feedback. It's usually quick,

98
00:04:53.600 --> 00:04:54.959
<v Speaker 2>cost effective.

99
00:04:54.720 --> 00:04:57.839
<v Speaker 1>Class mentions two ways for that, right, experts as evaluators

100
00:04:58.199 --> 00:04:59.879
<v Speaker 1>or evaluators supervising experts.

101
00:05:00.079 --> 00:05:04.360
<v Speaker 2>'s then you've got focus groups, more qualitative, subjective, good

102
00:05:04.399 --> 00:05:09.120
<v Speaker 2>for exploring perceptions, figuring out what questions to ask, finding unexpected.

103
00:05:08.560 --> 00:05:10.040
<v Speaker 1>Issues, kind of exploratory.

104
00:05:10.160 --> 00:05:13.120
<v Speaker 2>Yeah, and surveys. Of course, you can gather objective stuff

105
00:05:13.160 --> 00:05:16.959
<v Speaker 2>like demographics, playtime, and subjective things like attitudes, emotions.

106
00:05:17.000 --> 00:05:20.639
<v Speaker 1>Pretty standard but useful, especially combined with other data like

107
00:05:20.639 --> 00:05:21.439
<v Speaker 1>game analytics.

108
00:05:21.480 --> 00:05:24.639
<v Speaker 2>Maybe absolutely. Surveys are easy to deploy and can be

109
00:05:24.720 --> 00:05:27.720
<v Speaker 2>powerful when triangulated. But then it gets really interesting. They

110
00:05:27.759 --> 00:05:29.839
<v Speaker 2>talk about physiological.

111
00:05:29.040 --> 00:05:33.639
<v Speaker 1>Measurements ah, okay, like biometrics.

112
00:05:32.600 --> 00:05:36.920
<v Speaker 2>Sort of electrodermal activity or EDA that measures sweat gland

113
00:05:36.959 --> 00:05:40.959
<v Speaker 2>activity basically indicating arousal or mental effort, hum.

114
00:05:41.600 --> 00:05:45.160
<v Speaker 1>And cardiovascular heart rate YEP, heart rate variability and so on.

115
00:05:45.600 --> 00:05:50.199
<v Speaker 1>Gives insight into overall physical and emotional response, and even

116
00:05:50.199 --> 00:05:53.800
<v Speaker 1>electro biography EMG which measures muscle tension.

117
00:05:54.199 --> 00:05:55.759
<v Speaker 2>Muscle tension, what does that tell you?

118
00:05:56.000 --> 00:05:59.319
<v Speaker 1>It can indicate things like anxiety or even cognitive load

119
00:05:59.399 --> 00:05:59.800
<v Speaker 1>or strain.

120
00:06:00.120 --> 00:06:03.360
<v Speaker 2>Wow, So really getting under the hood of the player's experience.

121
00:06:03.519 --> 00:06:06.639
<v Speaker 1>Definitely, And it's important to distincish between this objective data

122
00:06:06.639 --> 00:06:09.480
<v Speaker 1>from machines and subjective data what the player reports.

123
00:06:09.639 --> 00:06:13.040
<v Speaker 2>Right, there's always a trade off there in reliability versus richness.

124
00:06:13.160 --> 00:06:16.639
<v Speaker 1>Perhaps kind of ideally you want both. The book also

125
00:06:16.680 --> 00:06:21.040
<v Speaker 1>talks about formative versus summative evaluation. Okay, formative is during development,

126
00:06:21.079 --> 00:06:24.079
<v Speaker 1>right to guide design like think clouds or interviews.

127
00:06:24.240 --> 00:06:27.360
<v Speaker 2>Exactly, it's more dialogue based. Summative is at the end

128
00:06:27.519 --> 00:06:32.480
<v Speaker 2>assessing overall performance against goals, often using those psychophysiological measures

129
00:06:32.560 --> 00:06:33.560
<v Speaker 2>or self assessments.

130
00:06:33.920 --> 00:06:37.959
<v Speaker 1>Got it now, shifting gears a bit? How about assessing

131
00:06:38.040 --> 00:06:42.439
<v Speaker 1>what someone's learning in the game, but without stopping the

132
00:06:42.480 --> 00:06:43.279
<v Speaker 1>game for a test.

133
00:06:43.480 --> 00:06:46.120
<v Speaker 2>Ah, Yes, that's the idea behind stealth assessment.

134
00:06:46.160 --> 00:06:50.199
<v Speaker 1>From chapter three. Sealth assessment sounds intriguing. It is the.

135
00:06:50.199 --> 00:06:52.639
<v Speaker 2>Goal is to measure those harder to pin down twenty

136
00:06:52.680 --> 00:06:58.279
<v Speaker 2>first century skills, creativity systems, thinking, persistence, things traditional tests

137
00:06:58.360 --> 00:06:59.199
<v Speaker 2>often miss.

138
00:06:59.079 --> 00:07:02.360
<v Speaker 1>And crucially, without breaking that flow that engagement we talked

139
00:07:02.360 --> 00:07:03.199
<v Speaker 1>about precisely.

140
00:07:03.199 --> 00:07:05.680
<v Speaker 2>It provides feedback without interrupting the experience.

141
00:07:05.759 --> 00:07:08.480
<v Speaker 1>And they link this to something called CAGE, content agnostic

142
00:07:08.519 --> 00:07:09.240
<v Speaker 1>game engineering.

143
00:07:09.560 --> 00:07:12.560
<v Speaker 2>Right. CAGE tries to solve a common problem with older

144
00:07:12.639 --> 00:07:16.439
<v Speaker 2>serious games. They were too tied to specific educational content,

145
00:07:16.720 --> 00:07:19.079
<v Speaker 2>made them hard to reuse sometimes less engaging.

146
00:07:19.279 --> 00:07:22.319
<v Speaker 1>So CAGE aims to make the core game mechanics and

147
00:07:22.399 --> 00:07:25.240
<v Speaker 1>the assessment reusable across different subjects.

148
00:07:25.600 --> 00:07:28.560
<v Speaker 2>That's the goal. Build the assessment into the framework in

149
00:07:28.600 --> 00:07:31.759
<v Speaker 2>a content agnostic way so you can potentially reuse it,

150
00:07:32.000 --> 00:07:33.959
<v Speaker 2>maybe speed up development for new topics.

151
00:07:34.040 --> 00:07:36.920
<v Speaker 1>How do they actually do that stealth assessment within CAGE?

152
00:07:37.160 --> 00:07:41.519
<v Speaker 2>They mentioned methods like mouse tracking, analyzing cursor movements, and

153
00:07:41.560 --> 00:07:45.800
<v Speaker 2>emotion tracking software things like Visa, just DK or aft

154
00:07:45.839 --> 00:07:47.839
<v Speaker 2>dex which look at facial.

155
00:07:47.439 --> 00:07:51.480
<v Speaker 1>Expressions facial expressions yea to detect boredom or frustration.

156
00:07:51.720 --> 00:07:56.000
<v Speaker 2>Yeah potentially, though with mouse tracking there's a performance consideration.

157
00:07:56.079 --> 00:07:57.920
<v Speaker 2>Track too much and it might slow the.

158
00:07:57.879 --> 00:07:59.639
<v Speaker 1>Game down, a classic trade off.

159
00:08:00.120 --> 00:08:03.959
<v Speaker 2>All this data stealth or not feeds into educational data

160
00:08:03.959 --> 00:08:06.279
<v Speaker 2>mining EDM looking for patterns.

161
00:08:06.319 --> 00:08:09.720
<v Speaker 1>Okay, and they also mentioned indogenous versus exogenous games.

162
00:08:09.879 --> 00:08:13.839
<v Speaker 2>Ah, Right, Indogenous means the game mechanics and the learning

163
00:08:13.879 --> 00:08:18.480
<v Speaker 2>content are tightly linked, intrinsically connected. Exogenous is where they're separate,

164
00:08:18.560 --> 00:08:20.920
<v Speaker 2>Like playing a fun game than getting a quiz.

165
00:08:20.759 --> 00:08:22.920
<v Speaker 1>Old chocolate covered broccoli problem kind of.

166
00:08:23.000 --> 00:08:26.800
<v Speaker 2>Yeah. Endogenous games generally lead to better learning and more enjoyment.

167
00:08:26.839 --> 00:08:28.839
<v Speaker 2>It feels more integrated.

168
00:08:28.319 --> 00:08:30.800
<v Speaker 1>Makes sense. And this all feeds into a.

169
00:08:30.800 --> 00:08:36.000
<v Speaker 2>Student model exactly. It's like a profile that accumulates data, emotions, skills,

170
00:08:36.240 --> 00:08:39.919
<v Speaker 2>knowledge based on how the player interacts. It helps understand behavior,

171
00:08:40.039 --> 00:08:44.000
<v Speaker 2>give feedback, and this is key. Dynamically adapt the.

172
00:08:43.960 --> 00:08:46.320
<v Speaker 1>Game, adapt the game on the fly, Yeah.

173
00:08:46.159 --> 00:08:48.679
<v Speaker 2>To try and create an optimal learning zone, keep it

174
00:08:48.799 --> 00:08:53.080
<v Speaker 2>challenging but not frustrating. The book mentions validation work on

175
00:08:53.159 --> 00:08:57.000
<v Speaker 2>cage showing benefits for reuse and speed, and that adaptation

176
00:08:57.120 --> 00:08:59.840
<v Speaker 2>helps with boredom, though maybe less so for learners who

177
00:08:59.879 --> 00:09:02.879
<v Speaker 2>are already knew the material well. They even use dynamic

178
00:09:02.960 --> 00:09:04.960
<v Speaker 2>basion networks for the adaptation part.

179
00:09:05.240 --> 00:09:07.919
<v Speaker 1>Complex stuff. Yeah, Okay, let's move from the player experience

180
00:09:07.919 --> 00:09:10.600
<v Speaker 1>and assessment to the actual bones of the game. The

181
00:09:10.639 --> 00:09:13.000
<v Speaker 1>software architecture Chapter four right.

182
00:09:13.120 --> 00:09:16.799
<v Speaker 2>Chapter four tackles architecture, especially for mobile serious.

183
00:09:16.360 --> 00:09:20.600
<v Speaker 1>Games, mobile ads, constraints, doesn't it memory processing.

184
00:09:20.080 --> 00:09:23.399
<v Speaker 2>Power definitely, So how you structure the game the components,

185
00:09:23.519 --> 00:09:25.879
<v Speaker 2>how they talk to each other is critical for handling

186
00:09:25.919 --> 00:09:29.639
<v Speaker 2>data efficiently and distributing resource as well. Design patterns can

187
00:09:29.679 --> 00:09:30.480
<v Speaker 2>really help here.

188
00:09:30.399 --> 00:09:33.639
<v Speaker 1>So thinking about non functional requirements from the start, things

189
00:09:33.679 --> 00:09:37.960
<v Speaker 1>like complexity, coupling, performance, reusability absolutely crucial.

190
00:09:38.440 --> 00:09:41.720
<v Speaker 2>Interestingly, research by Mizutani mentioned in the chapter suggests that

191
00:09:41.759 --> 00:09:45.279
<v Speaker 2>while data driven design is common, things like test driven

192
00:09:45.320 --> 00:09:48.759
<v Speaker 2>development and applying standard design patterns are less frequent in

193
00:09:48.840 --> 00:09:50.440
<v Speaker 2>serious games than you might expect.

194
00:09:50.679 --> 00:09:52.200
<v Speaker 1>HU wonder why that is.

195
00:09:52.320 --> 00:09:56.720
<v Speaker 2>Could be various reasons, maybe team composition, project pressures. The

196
00:09:56.799 --> 00:10:00.679
<v Speaker 2>chapter uses an example Android game to illustrate points, even

197
00:10:00.720 --> 00:10:05.279
<v Speaker 2>mentioning how UI color choices might impact usability like blue.

198
00:10:05.039 --> 00:10:08.919
<v Speaker 1>For calm, subtle things matter. How do they suggest evaluating

199
00:10:08.919 --> 00:10:10.120
<v Speaker 1>the architecture itself?

200
00:10:10.320 --> 00:10:15.519
<v Speaker 2>They look at metrics complexity like cyclomatic complexity CCM and

201
00:10:15.600 --> 00:10:20.360
<v Speaker 2>coupling between objects CBO. Basically how complicated and interconnected the

202
00:10:20.399 --> 00:10:20.799
<v Speaker 2>code is?

203
00:10:20.840 --> 00:10:23.039
<v Speaker 1>Okay, standard software metrics yeah, and.

204
00:10:23.000 --> 00:10:25.960
<v Speaker 2>They use statistical correlation Spearman correlation to see how these

205
00:10:26.000 --> 00:10:28.440
<v Speaker 2>relate and to derive a sort of quality factor for

206
00:10:28.519 --> 00:10:31.519
<v Speaker 2>code paths. And the main point is evaluating the design

207
00:10:31.559 --> 00:10:34.879
<v Speaker 2>early saves time and money later by catching potential problems

208
00:10:34.919 --> 00:10:37.759
<v Speaker 2>like defects and helping prioritize testing efforts.

209
00:10:37.840 --> 00:10:40.240
<v Speaker 1>Makes sense, find problems before they get baked in. Did

210
00:10:40.240 --> 00:10:41.360
<v Speaker 1>they find patterns helped?

211
00:10:41.600 --> 00:10:45.360
<v Speaker 2>Yes, they found that implementing patterns like wrapper and MBC

212
00:10:45.759 --> 00:10:48.960
<v Speaker 2>tended to result in code sequences with better quality scores

213
00:10:49.000 --> 00:10:51.399
<v Speaker 2>based on those complexity and coupling metrics.

214
00:10:51.759 --> 00:10:55.080
<v Speaker 1>Okay, so good architecture matters. Now let's look at a

215
00:10:55.240 --> 00:11:00.279
<v Speaker 1>very specific, quite high stakes application Chapter five and this

216
00:11:00.519 --> 00:11:02.200
<v Speaker 1>en Trust platform.

217
00:11:02.360 --> 00:11:05.840
<v Speaker 2>Ah. Yes, en Trust. This is a serious game platform

218
00:11:05.879 --> 00:11:10.080
<v Speaker 2>specifically designed for assessing clinical decision making in medical residents.

219
00:11:09.759 --> 00:11:13.080
<v Speaker 1>Right, judging their readiness for entrustment, basically being trusted to

220
00:11:13.159 --> 00:11:14.799
<v Speaker 1>perform tasks independently.

221
00:11:14.960 --> 00:11:18.600
<v Speaker 2>Exactly. Medical education is shifting more towards competency based assessment.

222
00:11:18.679 --> 00:11:21.159
<v Speaker 2>It's not just did you pass the test? But can

223
00:11:21.200 --> 00:11:23.320
<v Speaker 2>you actually do this safely and effectively?

224
00:11:23.480 --> 00:11:26.559
<v Speaker 1>And traditional observation has limits, right, depends on the case

225
00:11:26.600 --> 00:11:28.840
<v Speaker 1>that they happen to see faculty time potential bias.

226
00:11:28.960 --> 00:11:34.320
<v Speaker 2>Precisely, Virtual patient simulations like interruest offer objectivity, reproducibility. You

227
00:11:34.320 --> 00:11:38.799
<v Speaker 2>can create standardized scenarios measure performance consistently potentially reduced bias.

228
00:11:39.039 --> 00:11:41.600
<v Speaker 1>What does en trust actually do? What are its features?

229
00:11:41.879 --> 00:11:45.840
<v Speaker 2>It's pretty comprehensive. There's a case library for creating scenarios,

230
00:11:46.159 --> 00:11:51.279
<v Speaker 2>specifying how interventions affect vials, scoring actions, a virtual patient

231
00:11:51.320 --> 00:11:56.879
<v Speaker 2>generation tool for customization age, sex, BMI, even physical abnormalities.

232
00:11:57.080 --> 00:11:59.399
<v Speaker 1>Really detailed customization for diversity.

233
00:11:59.519 --> 00:12:03.159
<v Speaker 2>Yeah, you can set starting vital signs and choose algorithms

234
00:12:03.159 --> 00:12:06.799
<v Speaker 2>for how they change realistically, like simulating shock or sepsis.

235
00:12:07.120 --> 00:12:11.240
<v Speaker 2>Specify physical exam findings, what orders are available labs, meds

236
00:12:11.360 --> 00:12:14.159
<v Speaker 2>procedures and their outcomes and scoring effects.

237
00:12:14.159 --> 00:12:17.120
<v Speaker 1>It's very granular, sounds powerful. Did they test it? Was

238
00:12:17.159 --> 00:12:18.039
<v Speaker 1>there a pilot study?

239
00:12:18.200 --> 00:12:20.960
<v Speaker 2>Yes, and the pilot study showed promising results. It was

240
00:12:20.960 --> 00:12:24.399
<v Speaker 2>able to discriminate between surgical residents at different training levels

241
00:12:24.480 --> 00:12:28.000
<v Speaker 2>PGI levels when assessing their management of inguinal hernias.

242
00:12:28.120 --> 00:12:31.679
<v Speaker 1>So higher PGI level generally meant better score on entrust.

243
00:12:31.759 --> 00:12:34.759
<v Speaker 2>That's what they found a positive correlation. It also seemed

244
00:12:34.759 --> 00:12:38.480
<v Speaker 2>to capture performance on critical decision points in complex cases

245
00:12:38.720 --> 00:12:40.960
<v Speaker 2>like strangulated hernias.

246
00:12:40.759 --> 00:12:44.039
<v Speaker 1>So it suggests feasibility and some initial validity for using

247
00:12:44.039 --> 00:12:47.320
<v Speaker 1>this kind of platform for objective assessment, potentially informing those

248
00:12:47.320 --> 00:12:49.559
<v Speaker 1>crucial entrustment decisions exactly.

249
00:12:49.600 --> 00:12:51.720
<v Speaker 2>It's a really interesting application.

250
00:12:51.360 --> 00:12:55.159
<v Speaker 1>Building on that idea of assessment and adaptation. Chapter six

251
00:12:55.480 --> 00:12:58.639
<v Speaker 1>dies into using machine learning mL in serious games.

252
00:12:58.799 --> 00:13:02.639
<v Speaker 2>Right, this is a growing trend using mL not just

253
00:13:02.679 --> 00:13:05.519
<v Speaker 2>for assessment like we touched on with Stealth assessment, but

254
00:13:05.559 --> 00:13:08.120
<v Speaker 2>also to automatically adapt the game.

255
00:13:07.919 --> 00:13:13.840
<v Speaker 1>Itself, personalizing the experience basically to reduce frustration keep players engaged.

256
00:13:13.960 --> 00:13:16.159
<v Speaker 2>That's the aim. The chapter lays out a kind of

257
00:13:16.240 --> 00:13:19.159
<v Speaker 2>general four phase methodology if you want it to take

258
00:13:19.240 --> 00:13:23.000
<v Speaker 2>an existing non adaptive game and add mL to it.

259
00:13:23.159 --> 00:13:24.200
<v Speaker 1>Okay, what are the steps?

260
00:13:24.360 --> 00:13:28.399
<v Speaker 2>First, identify a game that could actually benefit from adaptation. Second,

261
00:13:28.519 --> 00:13:31.120
<v Speaker 2>model the gameplay tasks and how they relate to the

262
00:13:31.159 --> 00:13:33.600
<v Speaker 2>learner's ability or the competencies you're targeting.

263
00:13:33.679 --> 00:13:35.759
<v Speaker 1>Makes sense, Know what you want to adapt and why.

264
00:13:36.159 --> 00:13:39.639
<v Speaker 2>Third is the technical part, Actually build the mL models

265
00:13:39.679 --> 00:13:43.279
<v Speaker 2>and integrate them into the game's code. And fourth, critically

266
00:13:43.440 --> 00:13:46.279
<v Speaker 2>evaluate if the adaptive version is actually better than the

267
00:13:46.320 --> 00:13:49.360
<v Speaker 2>original does it improve learning or engagement?

268
00:13:49.600 --> 00:13:52.759
<v Speaker 1>That evaluation part sounds crucial, But are their challenges in

269
00:13:52.840 --> 00:13:53.200
<v Speaker 1>doing this?

270
00:13:53.559 --> 00:13:53.679
<v Speaker 2>Oh?

271
00:13:53.759 --> 00:13:53.960
<v Speaker 1>Yes?

272
00:13:54.240 --> 00:13:59.200
<v Speaker 2>The chapter highlights five common ones first, selecting the right

273
00:13:59.320 --> 00:14:02.039
<v Speaker 2>data to feel the mL model garbage in.

274
00:14:02.120 --> 00:14:04.480
<v Speaker 1>Garbage out right, always it Else.

275
00:14:04.399 --> 00:14:08.240
<v Speaker 2>Choosing which game elements to adapt what makes the most impact.

276
00:14:08.480 --> 00:14:09.120
<v Speaker 2>Then there's the.

277
00:14:09.039 --> 00:14:11.759
<v Speaker 1>Cold star problem, like a recommendation engine with no.

278
00:14:11.799 --> 00:14:15.120
<v Speaker 2>History exactly, how do you personalize when you have no

279
00:14:15.240 --> 00:14:18.960
<v Speaker 2>data yet? Maybe use existing data or generate synthetic data

280
00:14:19.000 --> 00:14:22.279
<v Speaker 2>to start Tricky. Another is figuring out how often to

281
00:14:22.320 --> 00:14:27.440
<v Speaker 2>adapt between sessions levels during tasks. There are trade offs

282
00:14:27.480 --> 00:14:29.279
<v Speaker 2>in computational cost and impact on.

283
00:14:29.240 --> 00:14:31.320
<v Speaker 1>The player, right, Adapting too much could.

284
00:14:31.120 --> 00:14:34.759
<v Speaker 2>Be jarring and maybe the biggest challenge proving that adaptation

285
00:14:34.919 --> 00:14:39.159
<v Speaker 2>actually improves learning, not just engagement. Sometimes more fun doesn't

286
00:14:39.159 --> 00:14:40.879
<v Speaker 2>equal more effective education a.

287
00:14:40.799 --> 00:14:44.200
<v Speaker 1>Really important distinction to make. So evaluate both the engagement

288
00:14:44.279 --> 00:14:45.360
<v Speaker 1>and the learning value.

289
00:14:45.360 --> 00:14:47.279
<v Speaker 2>Definitely you need evidence for both.

290
00:14:47.360 --> 00:14:51.919
<v Speaker 1>Okay, so we've covered complexity, evaluation, adaptation. Where does the

291
00:14:51.919 --> 00:14:54.360
<v Speaker 1>field go from here? What are the big future directions

292
00:14:54.440 --> 00:14:54.960
<v Speaker 1>or challenges?

293
00:14:55.120 --> 00:14:55.279
<v Speaker 2>Yeah?

294
00:14:55.399 --> 00:14:56.840
<v Speaker 1>Chapter seven and thirteen touch.

295
00:14:56.679 --> 00:14:59.720
<v Speaker 2>On this, right they do. Chapter seven revisits that idea

296
00:14:59.720 --> 00:15:03.200
<v Speaker 2>of t ansfering strategies from entertainment games. They give examples

297
00:15:03.200 --> 00:15:06.879
<v Speaker 2>like games tackling serious themes effectively hell Blade and Psychosis

298
00:15:06.960 --> 00:15:07.840
<v Speaker 2>as mentioned.

299
00:15:07.600 --> 00:15:11.600
<v Speaker 1>Or those simulator's truck driving PC building that are surprisingly

300
00:15:11.639 --> 00:15:15.559
<v Speaker 1>engaging but also teach real world skills sort of exactly.

301
00:15:15.720 --> 00:15:19.120
<v Speaker 2>They also talk about emergent possibilities, how game design can

302
00:15:19.200 --> 00:15:23.960
<v Speaker 2>lead to unexpected player experiences, and modding again as a

303
00:15:23.960 --> 00:15:28.320
<v Speaker 2>way to modify and transfer serious games. Emphasizing contexts and.

304
00:15:28.360 --> 00:15:30.639
<v Speaker 1>AI emotion modeling comes up again too.

305
00:15:30.679 --> 00:15:33.840
<v Speaker 2>Yes, the idea that understanding player emotion can lead to

306
00:15:33.840 --> 00:15:37.519
<v Speaker 2>better design. They introduce this concept of personality vectors for

307
00:15:37.759 --> 00:15:39.600
<v Speaker 2>NPC's non player characters.

308
00:15:39.759 --> 00:15:43.639
<v Speaker 1>Personality vectors like giving AI characters more nuanced behavior.

309
00:15:43.440 --> 00:15:46.039
<v Speaker 2>Kind of They give examples like patrolling guards or poker

310
00:15:46.080 --> 00:15:49.360
<v Speaker 2>players behaving more realistically. This could be huge for intelligent

311
00:15:49.360 --> 00:15:52.559
<v Speaker 2>tutors or health scenarios, making interactions feel more genuine.

312
00:15:52.600 --> 00:15:55.840
<v Speaker 1>That sounds potentially very powerful. What about the grand challenges

313
00:15:55.919 --> 00:15:57.120
<v Speaker 1>laid out in chapter thirteen?

314
00:15:57.440 --> 00:16:01.360
<v Speaker 2>Chapter thirteen summarizes several big ones, like the need for

315
00:16:01.519 --> 00:16:08.519
<v Speaker 2>software engineering methods, specifically for serious games. We need tailored approaches.

316
00:16:08.279 --> 00:16:10.639
<v Speaker 1>Not just borrowing from general software engineering right.

317
00:16:11.000 --> 00:16:15.000
<v Speaker 2>Also establishing common terminology, a shared ontology, so everyone speaking

318
00:16:15.039 --> 00:16:19.559
<v Speaker 2>the same language. Improving reusability and maintainability always a challenge

319
00:16:19.559 --> 00:16:22.039
<v Speaker 2>in software, but maybe more so here.

320
00:16:22.120 --> 00:16:25.759
<v Speaker 1>Quality assurance and testing too, I imagine have unique aspects.

321
00:16:25.279 --> 00:16:29.360
<v Speaker 2>Definitely, and developing better ways to monitor and adapt gameplay

322
00:16:29.559 --> 00:16:34.600
<v Speaker 2>safely avoiding unwanted side effects, enabling truly player centric design.

323
00:16:34.919 --> 00:16:38.519
<v Speaker 2>They stress needing uniform data, logues and iterative design.

324
00:16:38.759 --> 00:16:41.600
<v Speaker 1>Consistent data is key for that monitoring and adaptation.

325
00:16:41.799 --> 00:16:46.600
<v Speaker 2>Absolutely, and finally, a big opportunity creating effective serious games

326
00:16:46.639 --> 00:16:50.480
<v Speaker 2>for teaching software engineering itself, using gamification and AI for

327
00:16:50.519 --> 00:16:52.919
<v Speaker 2>personalized learning paths for developers.

328
00:16:52.519 --> 00:16:55.000
<v Speaker 1>Turning the tools back on ourselves essentially.

329
00:16:54.720 --> 00:16:57.039
<v Speaker 2>Pretty much So. Yeah, lots of challenges, but also lots

330
00:16:57.080 --> 00:16:58.960
<v Speaker 2>of opportunities for research and advancement.

331
00:16:59.039 --> 00:17:01.080
<v Speaker 1>It really sounds like a dynamic field with a lot

332
00:17:01.159 --> 00:17:02.039
<v Speaker 1>still to figure out.

333
00:17:02.320 --> 00:17:05.519
<v Speaker 2>No question, these challenges are where the next breakthroughs will

334
00:17:05.559 --> 00:17:06.079
<v Speaker 2>likely happen.

335
00:17:06.160 --> 00:17:08.599
<v Speaker 1>Okay, let's try and wrap this up. We've covered a

336
00:17:08.599 --> 00:17:11.200
<v Speaker 1>lot of ground in this deep dive. We started with

337
00:17:11.240 --> 00:17:14.039
<v Speaker 1>that inherent complexity pulling from so many disciplines.

338
00:17:14.160 --> 00:17:17.799
<v Speaker 2>Right then, how gamification is sneaking into software development itself

339
00:17:18.240 --> 00:17:22.240
<v Speaker 2>and the crucial need for solid user experience evaluation using

340
00:17:22.400 --> 00:17:24.559
<v Speaker 2>various methods, even physiological ones.

341
00:17:24.759 --> 00:17:28.480
<v Speaker 1>We looked at stealth assessment measuring learning without interrupting flow

342
00:17:28.519 --> 00:17:33.319
<v Speaker 1>and dynamic adaptation using machine learning, plus the architectural nuts

343
00:17:33.319 --> 00:17:35.279
<v Speaker 1>and bolts, especially for mobile.

344
00:17:35.359 --> 00:17:39.160
<v Speaker 2>Don't forget the specific applications like the Entrust platform for

345
00:17:39.200 --> 00:17:43.519
<v Speaker 2>assessing medical decision making showing real world impact true.

346
00:17:43.599 --> 00:17:46.599
<v Speaker 1>And finally, we touched on those future directions transferring ideas

347
00:17:46.599 --> 00:17:50.599
<v Speaker 1>from entertainment, AI personality, and the big challenges ahead like

348
00:17:50.640 --> 00:17:52.880
<v Speaker 1>specialized methodologies and better adaptation.

349
00:17:53.319 --> 00:17:57.039
<v Speaker 2>It's clear that blending rigorous engineering with engaging game design

350
00:17:57.480 --> 00:18:02.599
<v Speaker 2>gives us some incredibly powerful tools for education, training, maybe

351
00:18:02.680 --> 00:18:03.519
<v Speaker 2>much more so.

352
00:18:03.680 --> 00:18:06.759
<v Speaker 1>The final thought for you, the listener, think about those

353
00:18:06.759 --> 00:18:11.319
<v Speaker 1>principles of engagement and motivation from games. How could they

354
00:18:11.319 --> 00:18:14.599
<v Speaker 1>apply elsewhere in your life? Maybe in learning something new,

355
00:18:14.720 --> 00:18:17.599
<v Speaker 1>or even making mundane tasks feel a bit more well

356
00:18:18.240 --> 00:18:19.400
<v Speaker 1>game like and rewarding.

357
00:18:19.799 --> 00:18:24.200
<v Speaker 2>What game mechanics could make tricky things more approachable? Definitely

358
00:18:24.200 --> 00:18:25.599
<v Speaker 2>some interesting food for thought there.

359
00:18:25.720 --> 00:18:28.400
<v Speaker 1>Absolutely If this sparked your interest, do check out the

360
00:18:28.440 --> 00:18:31.640
<v Speaker 1>book Software Engineering for Games and Serious Contexts and the

361
00:18:31.759 --> 00:18:34.599
<v Speaker 1>related research for a much deeper look. Thanks for joining

362
00:18:34.680 --> 00:18:35.440
<v Speaker 1>us on the deep dive.