|
Contents |
6 |
|
|
Contributing Authors |
8 |
|
|
Preface |
16 |
|
|
I EVALUATION METHODOLOGY |
21 |
|
|
Chapter 1 THE BLIND MEN AND THE ELEPHANT REVISITED |
23 |
|
|
1. Introduction |
24 |
|
|
2. The Taxonomy |
26 |
|
|
2.1 Believability |
32 |
|
|
2.2 Sociability |
34 |
|
|
2.3 Task and Application Domains |
36 |
|
|
2.4 Agency and Computational Issues |
37 |
|
|
3. Applying the Taxonomy |
38 |
|
|
4. On Production Values |
40 |
|
|
5. Further Classi.cation |
41 |
|
|
6. Conclusions |
42 |
|
|
Notes |
43 |
|
|
References |
43 |
|
|
Chapter 2 EMBODIED CONVERSATIONAL AGENTS ON A COMMON GROUND |
47 |
|
|
1. Introduction |
48 |
|
|
1.1 Motivations and Problems |
49 |
|
|
2. ECAs from a Design Perspective |
50 |
|
|
2.1 The Embodiment |
52 |
|
|
2.2 The Mental Aspects |
56 |
|
|
2.3 Implementation Aspects |
59 |
|
|
2.4 Range of Applicability |
60 |
|
|
3. On Evaluation Methodology |
60 |
|
|
3.1 Why to Evaluate? |
61 |
|
|
3.2 How to De.ne the Evaluation Variables? |
66 |
|
|
3.3 Testing by what Users? |
68 |
|
|
3.4 How to Collect and Evaluate Data? |
71 |
|
|
4. Dimensions of Evaluation |
73 |
|
|
4.1 Usability |
74 |
|
|
4.2 Evaluation of User Perception of ECAs |
76 |
|
|
5. Conclusions |
81 |
|
|
Notes |
82 |
|
|
References |
83 |
|
|
Chapter 3 EMPIRICAL EVALUATION METHODOLOGY FOR EMBODIED CONVERSATIONAL AGENTS |
87 |
|
|
1. Introduction |
88 |
|
|
2. Types of Evaluation Research |
88 |
|
|
2.1 Star Life Cycle |
89 |
|
|
2.2 Formative and Summative Evaluation |
91 |
|
|
3. Research Model, Research Question and Construct |
92 |
|
|
3.1 Research Model |
92 |
|
|
3.2 Research Questions |
94 |
|
|
3.3 Psychological Construct |
95 |
|
|
4. Research Strategy |
96 |
|
|
4.1 Survey |
97 |
|
|
4.2 Experiment |
98 |
|
|
4.3 Case Study |
99 |
|
|
5. Data Collection Methods |
100 |
|
|
5.1 Qualitative Methods |
101 |
|
|
5.2 Quantitative Methods |
102 |
|
|
5.3 More Data Collection Methods |
106 |
|
|
6. Samples, Reliability and Validity |
106 |
|
|
6.1 Samples |
106 |
|
|
6.2 Reliability |
108 |
|
|
6.3 Validity |
110 |
|
|
7. Data Analysis |
112 |
|
|
8. Concluding: Guidelines for Evaluating ECAs |
114 |
|
|
Acknowledgments |
116 |
|
|
Notes |
116 |
|
|
References |
116 |
|
|
Chapter 4 EVALUATING USERS’ REACTIONS TO HUMAN-LIKE INTERFACES |
121 |
|
|
1. Evaluation of Dialogue Systems |
122 |
|
|
1.1 Evaluation of User’s Satisfaction |
122 |
|
|
1.2 Evaluation Criteria for Multimodal Dialogue Systems |
123 |
|
|
2. Prosodic Cues and Non-verbal Behaviour as new Evaluation Measures |
124 |
|
|
2.1 Prosodic and Visual Cues of Emotions |
125 |
|
|
2.2 Prosodic and Visual Cues of Emotions and Evaluation |
125 |
|
|
3. The Investigation |
126 |
|
|
3.1 Material |
126 |
|
|
3.2 Analysis of Prosodic Cues |
130 |
|
|
3.3 Analysis of Non-verbal Communicative Behaviour |
135 |
|
|
4. Conclusions and Further Investigation |
140 |
|
|
Acknowledgments |
141 |
|
|
Notes |
141 |
|
|
References |
141 |
|
|
II THE USER IN FOCUS |
145 |
|
|
Chapter 5 USER-CENTRED DESIGN AND EVALUATION OF AFFECTIVE INTERFACES |
147 |
|
|
1. Introduction |
148 |
|
|
2. Underlying Philosophy and Method |
149 |
|
|
2.1 Our Philosophy |
151 |
|
|
2.2 Our Method |
152 |
|
|
3. Studies of Three Affective Interfaces |
157 |
|
|
4. Agneta & Frida |
158 |
|
|
4.1 Non-correlation of Measurements |
159 |
|
|
4.2 Narrative Experience |
161 |
|
|
4.3 Implications for Design Method |
162 |
|
|
5. The Influencing Machine |
163 |
|
|
5.1 Study Method |
164 |
|
|
5.2 The First In.uencing Machine Study |
166 |
|
|
5.3 The Second Influencing Machine Study |
167 |
|
|
5.4 Implications for Design Method |
169 |
|
|
6. SenToy and FantasyA |
170 |
|
|
6.1 Wizard of Oz |
171 |
|
|
6.2 Second Study of SenToy Used in FantasyA |
173 |
|
|
6.3 Implications for Design Method |
174 |
|
|
7. Discussion |
175 |
|
|
Acknowledgments |
177 |
|
|
Notes |
177 |
|
|
References |
177 |
|
|
Chapter 6 ‘USER AS ASSESSOR’ APPROACH TO EMBODIED CONVERSATIONAL AGENTS |
181 |
|
|
1. Introduction |
182 |
|
|
2. Attention as an Example of the ‘User as Assessor’ Approach |
186 |
|
|
2.1 How Do Humans Attend? |
186 |
|
|
2.2 Conceptualizing Apparent Attention |
188 |
|
|
3. Creating Apparently Attentive ECAs |
190 |
|
|
3.1 Apparent Selectivity in ECAs |
190 |
|
|
3.2 Apparent Breadth in ECAs |
195 |
|
|
4. Conclusion |
199 |
|
|
Notes |
201 |
|
|
References |
201 |
|
|
III EVALUATION OF ECAS |
209 |
|
|
Chapter 7 MORE ABOUT BROWS |
211 |
|
|
1. Introduction |
212 |
|
|
2. About Brows |
213 |
|
|
3. Materials |
216 |
|
|
3.1 Speech |
216 |
|
|
3.2 Animations |
218 |
|
|
4. Experiment 1: Subjective Preference |
219 |
|
|
4.1 Method |
219 |
|
|
4.2 Results (Dutch) |
220 |
|
|
4.3 Results (Italian) |
220 |
|
|
4.4 Discussion |
221 |
|
|
5. Experiment 2: Perceived Prominence |
221 |
|
|
5.1 Method |
221 |
|
|
5.2 Results (Dutch) |
222 |
|
|
5.3 Results (Italian) |
224 |
|
|
5.4 Discussion |
224 |
|
|
6. Experiment 3: Functional Analysis |
225 |
|
|
6.1 Method |
225 |
|
|
6.2 Results (Dutch) |
226 |
|
|
6.3 Results (Italian) |
227 |
|
|
6.4 Discussion |
227 |
|
|
7. General Discussion |
228 |
|
|
7.1 Eyebrows in Dutch and Italian |
228 |
|
|
7.2 About Analysis-by-Synthesis |
230 |
|
|
7.3 Analysis-by-observation |
231 |
|
|
Acknowledgments |
233 |
|
|
Notes |
233 |
|
|
References |
234 |
|
|
Chapter 8 EVALUATION OF MULTIMODAL BEHAVIOUR OF EMBODIED AGENTS |
237 |
|
|
1. Introduction |
238 |
|
|
2. Experimental Setting |
240 |
|
|
2.1 Participants |
240 |
|
|
2.2 Apparatus |
241 |
|
|
2.3 Scenarios |
241 |
|
|
2.4 Independent Variables |
242 |
|
|
2.5 Generation of Multimodal Behaviour |
245 |
|
|
2.6 Dependent Variables |
246 |
|
|
2.7 Data Analysis |
247 |
|
|
3. Results |
247 |
|
|
3.1 Subjective Variables |
247 |
|
|
3.2 Recall Performance |
250 |
|
|
4. Discussion |
251 |
|
|
4.1 Effects of Multimodal Strategies |
252 |
|
|
4.2 Effects of ECAs’ Appearance |
253 |
|
|
4.3 Additional Results |
254 |
|
|
5. Conclusions and Future Directions |
254 |
|
|
Acknowledgments |
256 |
|
|
Notes |
256 |
|
|
References |
256 |
|
|
Chapter 9 ECA AS USER INTERFACE PARADIGM |
259 |
|
|
1. Introduction |
260 |
|
|
1.1 Our Research Objectives |
262 |
|
|
2. Research Framework |
264 |
|
|
2.1 Features of the User |
265 |
|
|
2.2 Features of the ECA |
267 |
|
|
2.3 Features of the Task |
270 |
|
|
2.4 Interaction of Variables |
273 |
|
|
2.5 Approaches to Assessing ECAs |
274 |
|
|
3. An Experimental Study |
274 |
|
|
3.1 Goal and Hypotheses |
275 |
|
|
3.2 Participants, Materials, and Procedure |
276 |
|
|
3.3 Results |
279 |
|
|
3.4 Additional Observations from the Experiment |
282 |
|
|
4. Conclusions |
283 |
|
|
Notes |
284 |
|
|
References |
284 |
|
|
IV EVALUATION OF APPLICATIONS |
289 |
|
|
Chapter 10 TALKING TO DIGITAL FISH |
291 |
|
|
1. Introduction |
292 |
|
|
1.1 Evaluating Animated Characters in Educational Software |
293 |
|
|
1.2 Goals of the Study |
294 |
|
|
2. Methods |
294 |
|
|
2.1 Participants, Task, and Procedure |
294 |
|
|
2.2 Simulation Environment |
296 |
|
|
2.3 Text to Speech Manipulation |
297 |
|
|
2.4 Research Design and Analyses |
298 |
|
|
2.5 Data Coding and Dependent Measures |
299 |
|
|
3. Results |
302 |
|
|
3.1 Engagement in Interface and Ease of Use |
302 |
|
|
3.2 Distribution of Question Types |
304 |
|
|
3.3 Impact of TTS Voice Type on Child Queries |
304 |
|
|
4. Discussion |
305 |
|
|
4.1 Acoustic Characteristics of Animated Character Design |
305 |
|
|
4.2 Conversational Interfaces as Educational Interfaces |
308 |
|
|
4.3 Conclusion |
309 |
|
|
Acknowledgments |
310 |
|
|
Notes |
310 |
|
|
References |
310 |
|
|
Chapter 11 EXPERIMENTAL EVALUATION OF THE USE OF ECAS IN ECOMMERCE APPLICATIONS |
313 |
|
|
1. Introduction |
314 |
|
|
2. Experimental Approach |
315 |
|
|
3. The Phoebe Experiment |
317 |
|
|
3.1 Experimental Procedure |
319 |
|
|
3.2 The Usability Questionnaire |
321 |
|
|
3.3 Results |
321 |
|
|
3.4 Summary |
324 |
|
|
4. The Voice Personae Experiment |
324 |
|
|
4.1 Voice Personae |
327 |
|
|
4.2 Experimental Procedure |
328 |
|
|
4.3 Results |
329 |
|
|
4.4 Summary |
332 |
|
|
5. The Trust Experiment |
332 |
|
|
5.1 Experimental Procedure |
335 |
|
|
5.2 Results |
335 |
|
|
5.3 Summary |
338 |
|
|
6. Conclusion |
339 |
|
|
References |
340 |
|
|
Chapter 12 WHAT WE CAN LEARN FROM AVATAR-DRIVEN INTERNET COMMUNITIES |
343 |
|
|
1. Introduction |
344 |
|
|
2. The sysis NetLife |
346 |
|
|
2.1 The NetLife Platform |
346 |
|
|
2.2 The Flirtboat Application |
347 |
|
|
2.3 The derSpittelberg Application |
350 |
|
|
3. User Data Analysis |
351 |
|
|
3.1 Goals for Data Collection |
352 |
|
|
3.2 Methodology |
353 |
|
|
3.3 Generalized Avatar Pro.le |
355 |
|
|
3.4 Lifestyle Analysis |
360 |
|
|
4. Data Evaluation |
361 |
|
|
4.1 Evaluation Results |
362 |
|
|
5. Conclusion |
370 |
|
|
Acknowledgments |
371 |
|
|
Notes |
371 |
|
|
References |
372 |
|
|
More eBooks at www.ciando.com |
0 |
|