179:
Therefore, there is a high likelihood that the user models are not up to date. However, this first method allows the users to have full control over the collected data about them. It is their decision which information they are willing to provide. This possibility is missing in the second method. Adaptive changes in a system that learns users' preferences and needs only by interpreting their behavior might appear a bit opaque to the users, because they cannot fully understand and reconstruct why the system behaves the way it does. Moreover, the system is forced to collect a certain amount of data before it is able to predict the users' needs with the required accuracy. Therefore, it takes a certain learning time before a user can benefit from adaptive changes. However, afterwards these automatically adjusted user models allow a quite accurate adaptivity of the system. The hybrid approach tries to combine the advantages of both methods. Through collecting data by directly asking its users it gathers a first stock of information which can be used for adaptive changes. By learning from the users' interactions it can adjust the user models and reach more accuracy. Yet, the designer of the system has to decide, which of these information should have which amount of influence and what to do with learned data that contradicts some of the information given by a user.
239:: Expert systems are computer systems that emulate the decision-making ability of a human expert in order to help the user solving a problem in a specific area. Step by step they ask questions to identify the current problem and to find a solution. User models can be used to adapt to the current user's knowledge, differentiating between experts and novices. The system can assume, that experienced users are able to understand and answer more complex questions than someone who is new to the topic. Therefore, it can adjust the used vocabulary and the type of question which are presented to the user, thus reducing the steps needed to find a solution.
255:: Since user modeling allows the system to hold an internal representation of a specific user, different types of users can be simulated by artificially modeling them. Common types are "experts" or "novices" on the scope of the system or the usage of the system. Based on these characteristics user tests can be simulated. The SUPPLE project at University of Washington and the Inclusive User Model at University of Cambridge simulates interaction for users with visual, hearing and motor impairment.
233:: Unlike adaptive educational hypermedia systems intelligent tutoring systems are stand-alone systems. Their aim is to help students in a specific field of study. To do so, they build up a user model where they store information about abilities, knowledge and needs of the user. The system can now adapt to this user by presenting appropriate exercises and examples and offering hints and help where the user is most likely to need them.
205:. In this case information about a user is compared to that of other users of the same systems. Thus, if characteristics of the current user match those of another, the system can make assumptions about the current user by presuming that he or she is likely to have similar characteristics in areas where the model of the current user is lacking data. Based on these assumption the system then can perform adaptive changes.
196:
a dynamic adaption to the user is automatically performed by the system itself, based on the built user model. Thus, an adaptive system needs ways to interpret information about the user in order to make these adaptations. One way to accomplish this task is implementing rule-based filtering. In this
187:
Once a system has gathered information about a user it can evaluate that data by preset analytical algorithm and then start to adapt to the user's needs. These adaptations may concern every aspect of the system's behavior and depend on the system's purpose. Information and functions can be presented
178:
Though the first method is a good way to quickly collect main data it lacks the ability to automatically adapt to shifts in users' interests. It depends on the users' readiness to give information and it is unlikely that they are going to edit their answers once the registration process is finished.
105:
into common stereotypes. The system then adapts to this stereotype. The application therefore can make assumptions about a user even though there might be no data about that specific area, because demographic studies have shown that other users in this stereotype have the same characteristics. Thus,
156:
In this case users are not asked directly for their personal data and preferences, but this information is derived from their behavior while interacting with the system. The ways they choose to accomplish a tasks, the combination of things they takes interest in, these observations allow inferences
56:
is the actual representation in a given user model. The process of obtaining the user profile is called user modeling. Therefore, it is the basis for any adaptive changes to the system's behavior. Which data is included in the model depends on the purpose of the application. It can include personal
118:
Highly adaptive user models try to represent one particular user and therefore allow a very high adaptivity of the system. In contrast to stereotype based user models they do not rely on demographic statistics but aim to find a specific solution for each user. Although users can take great benefit
84:
Dynamic user models allow a more up to date representation of users. Changes in their interests, their learning progress or interactions with the system are noticed and influence the user models. The models can thus be updated and take the current needs and goals of the users into
27:
to the user's specific needs. The system needs to "say the 'right' thing at the 'right' time in the 'right' way". To do so it needs an internal representation of the user. Another common purpose is modeling specific kinds of users, including modeling of their skills and
217:: In an adaptive hypermedia system the displayed content and the offered hyperlinks are chosen on basis of users' specific characteristics, taking their goals, interests, knowledge and abilities into account. Thus, an adaptive hypermedia system aims to reduce the "
245:: The basic idea of recommender systems is to present a selection of items to the user which best fit his or her needs. This selection can be based on items the user has bookmarked, rated, bought, recently viewed, etc. Recommender systems are often used in
106:
stereotype based user models mainly rely on statistics and do not take into account that personal attributes might not match the stereotype. However, they allow predictions about a user even if there is rather little information about him or her.
173:
This approach is a mixture of the ones above. Users have to answer specific questions and give explicit feedback. Furthermore, their interactions with the system are observed and the derived information are used to automatically adjust the user
71:
Static user models are the most basic kinds of user models. Once the main data is gathered they are normally not changed again, they are static. Shifts in users' preferences are not registered and no learning algorithms are used to alter the
57:
information such as users' names and ages, their interests, their skills and knowledge, their goals and plans, their preferences and their dislikes or data about their behavior and their interactions with the system.
192:. In an adaptable system the user can manually change the system's appearance, behavior or functionality by actively selecting the corresponding options. Afterwards the system will stick to these choices. In an
143:
Mostly this kind of data gathering is linked with the registration process. While registering users are asked for specific facts, their likes and dislikes and their needs. Often the given answers can be altered
188:
according to the user's interests, knowledge or goals by displaying only relevant features, hiding information the user does not need, making proposals what to do next and so on. One has to distinguish between
227:: Being a subdivision of adaptive hypermedia the main focus of adaptive educational hypermedia lies on education, displaying content and hyperlinks corresponding to the user's knowledge on the field of study.
201:
of the system. The IF-conditions can check for specific user-information and if they match the THEN-branch is performed which is responsible for the adaptive changes. Another approach is based on
129:
23:
which describes the process of building up and modifying a conceptual understanding of the user. The main goal of user modeling is customization and
52:
associated with a specific user. A user model is a (data) structure that is used to capture certain characteristics about an individual user, and a
102:
580:
264:
A certain number of representation formats and standards are available for representing the users in computer systems, such as:
224:
20:
189:
24:
467:
Montaner, Miguel; LĂłpez, Beatriz; De La Rosa, Josep LluĂs (2003), "A Taxonomy of
Recommender Agents on the Internet",
230:
529:
398:
Piao, Guangyuan; Breslin, John G. (2018). "Inferring User
Interests in Microblogging Social Networks: A Survey".
282:
202:
29:
157:
about a specific user. The application dynamically learns from observing these interactions. Different
451:, Southampton University, Electronics and Computer Science University Road, Southampton, Hampshire, UK
278:
322:
214:
484:
425:
407:
242:
218:
167:
A hybrid approach which asks for explicit feedback and alters the user model by adaptive learning
515:
252:
32:, for use in automatic software-tests. User-models can thus serve as a cheaper alternative to
268:
60:
There are different design patterns for user models, though often a mixture of them is used.
476:
417:
353:
158:
150:
Learning users' preferences by observing and interpreting their interactions with the system
312:
307:
288:
193:
119:
from this high adaptivity, this kind of model needs to gather a lot of information first.
236:
198:
574:
49:
488:
429:
317:
98:
53:
37:
33:
444:
480:
421:
358:
272:
246:
501:
445:"An Evaluation of Adapted Hypermedia Techniques Using Static User Modelling"
294:
344:
Fischer, Gerhard (2001), "User
Modeling in Human-Computer Interaction",
555:
550:
449:
Proceedings of the 2nd
Workshop on Adaptive Hypertext and Hypermedia
412:
249:
but may also cover areas like social networks, websites, news, etc.
137:
Asking for specific facts while (first) interacting with the system
197:
case a set of IF... THEN... rules is established that covers the
502:"SUPPLE: Automatic Generation of Personalizable User Interfaces"
560:
565:
544:
383:
Johnson, Addie; Taatgen, Niels (2005), "User
Modeling",
48:
A user model is the collection and categorization of
271:(IMS – Learner Information Packaging, used in
291:(Justice with the Global Justice Extensible Markup)
221:" syndrome by presenting only relevant information.
545:User Modeling and User-Adapted Interaction (UMUAI)
516:"Computer Laboratory: Inclusive user interfaces"
378:
376:
374:
372:
370:
368:
387:, Lawrence Erlbaum Associates, pp. 424–439
161:algorithms may be used to accomplish this task.
132:in several ways. There are three main methods:
101:. Based on the gathered information users are
8:
462:
460:
458:
443:Hothi, Jatinder; Hall, Wendy (June 1998),
400:User Modeling and User-Adapted Interaction
346:User Modeling and User-Adapted Interaction
97:Stereotype based user models are based on
411:
357:
339:
337:
547:The Journal of Personalization Research
385:Handbook of human factors in Web design
333:
7:
532:, FIDIS Deliverable, October 2005.
14:
225:Adaptive educational hypermedia
128:Information about users can be
190:adaptive and adaptable systems
1:
561:User Modeling Conference 2018
556:User Modeling Conference 2007
91:Stereotype based user models
231:Intelligent tutoring system
112:Highly adaptive user models
597:
21:human–computer interaction
422:10.1007/s11257-018-9207-8
283:human resource management
581:Knowledge representation
297:(the Europass online CV)
528:Nabeth Thierry (2005),
481:10.1023/A:1022850703159
359:10.1023/A:1011145532042
203:collaborative filtering
36:but should not replace
551:CogTool Project at CMU
99:demographic statistics
19:is the subdivision of
30:declarative knowledge
25:adaptation of systems
539:External references
469:Artif. Intell. Rev.
323:Identity management
215:Adaptive hypermedia
78:Dynamic user models
243:Recommender system
219:lost in hyperspace
65:Static user models
183:System adaptation
588:
533:
526:
520:
519:
512:
506:
505:
498:
492:
491:
464:
453:
452:
440:
434:
433:
415:
395:
389:
388:
380:
363:
362:
361:
341:
159:machine learning
596:
595:
591:
590:
589:
587:
586:
585:
571:
570:
541:
536:
527:
523:
514:
513:
509:
500:
499:
495:
466:
465:
456:
442:
441:
437:
397:
396:
392:
382:
381:
366:
343:
342:
335:
331:
313:Cognitive model
308:Personalization
304:
262:
253:User-Simulation
211:
194:adaptive system
185:
126:
46:
12:
11:
5:
594:
592:
584:
583:
573:
572:
569:
568:
566:Hypertext 2018
563:
558:
553:
548:
540:
537:
535:
534:
521:
507:
493:
475:(4): 285–330,
454:
435:
406:(3): 277–329.
390:
364:
332:
330:
327:
326:
325:
320:
315:
310:
303:
300:
299:
298:
292:
286:
276:
261:
258:
257:
256:
250:
240:
237:Expert systems
234:
228:
222:
210:
207:
199:knowledge base
184:
181:
176:
175:
170:
169:
163:
162:
153:
152:
146:
145:
140:
139:
125:
124:Data gathering
122:
121:
120:
115:
114:
108:
107:
94:
93:
87:
86:
81:
80:
74:
73:
68:
67:
45:
42:
13:
10:
9:
6:
4:
3:
2:
593:
582:
579:
578:
576:
567:
564:
562:
559:
557:
554:
552:
549:
546:
543:
542:
538:
531:
525:
522:
517:
511:
508:
503:
497:
494:
490:
486:
482:
478:
474:
470:
463:
461:
459:
455:
450:
446:
439:
436:
431:
427:
423:
419:
414:
409:
405:
401:
394:
391:
386:
379:
377:
375:
373:
371:
369:
365:
360:
355:
351:
347:
340:
338:
334:
328:
324:
321:
319:
316:
314:
311:
309:
306:
305:
301:
296:
293:
290:
287:
284:
280:
277:
274:
270:
267:
266:
265:
259:
254:
251:
248:
244:
241:
238:
235:
232:
229:
226:
223:
220:
216:
213:
212:
208:
206:
204:
200:
195:
191:
182:
180:
172:
171:
168:
165:
164:
160:
155:
154:
151:
148:
147:
142:
141:
138:
135:
134:
133:
131:
123:
117:
116:
113:
110:
109:
104:
100:
96:
95:
92:
89:
88:
83:
82:
79:
76:
75:
70:
69:
66:
63:
62:
61:
58:
55:
51:
50:personal data
43:
41:
39:
35:
31:
26:
22:
18:
17:User modeling
524:
510:
496:
472:
468:
448:
438:
403:
399:
393:
384:
349:
345:
318:User profile
263:
186:
177:
166:
149:
136:
127:
111:
90:
77:
64:
59:
54:user profile
47:
38:user testing
34:user testing
16:
15:
144:afterwards.
413:1712.07691
329:References
273:e-learning
247:e-commerce
103:classified
44:Background
352:: 65–86,
281:(used in
260:Standards
575:Category
489:16544257
302:See also
295:Europass
130:gathered
85:account.
430:3847937
269:IMS-LIP
174:models.
530:Models
487:
428:
279:HR-XML
209:Usages
72:model.
485:S2CID
426:S2CID
408:arXiv
289:JXDM
477:doi
418:doi
354:doi
577::
483:,
473:19
471:,
457:^
447:,
424:.
416:.
404:28
402:.
367:^
350:11
348:,
336:^
40:.
518:.
504:.
479::
432:.
420::
410::
356::
285:)
275:)
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.