I was actually thinking about a more traditional story adaptation, in games which are heavily based on story lines, RPGs and such like. However, emergent storytelling is still valid, and you're right, RagingLion, Left4Dead is very good at adapting to one emotion, stress. It's the only emotion they look at, but the data they collect to deduce stress levels is quite vast. Although I knew of this game I hadn't actually tried playing it until today, so my personal experience is very limited here. But having read up on the Director, I am more than a little impressed. So I withdraw my earlier statement saying this has not been done yet, and replace is by saying that to my knowledge no one has yet developed a game which successfully adapts to a range of emotions. This is a very good start though! :)
Thanks for pointing me in this direction, I'm not sure how I missed this a year ago! :P
But thinking in terms of more traditional story based games, with a non-emergent storyline, how would you answer my original questions?
Oh and if there are any more games like L4D, or more points to which you wish to refer re this game, please, bung them in too! :D
And, yes, ahoodedfigure, that's exactly what I was getting at! :P
Phewsie's forum posts
Indeed, everything will be greatly subjective. The question is how good can we get at guessing/deducing how the player is feeling..? I'm guessing with time we can probably get pretty good, certainly through use of machine learning algorithms, and accurate emotion classifiers. But I guess it'll take some time..
I think using the drama curve used by films is a good place to start when attempting to induce 'fun' which you refer to. Continuous stress and nothing but is probably not fun for most people, nor is slow and easy. The trick is to find a good balance, allowing tension to build, build, build and then chill after a climax. Then start the process all over again. Perhaps a good idea would be to attempt to construct the ideal drama curve as part of the machine learning, rendering the system user-dependent, but potentially very clever at not only guessing what you are feeling, but ensuring the optimal level of enjoyment, challenge, pace and engagement for you..?
BTW, I really like your push, pull theory. I've never really thought of games in that way, but you're definitely right! :)
@ahoodedfigure:
The wiki definition is a pretty good one actually. It doesn't contain heeps of information, but I don't want to drown you on this particular topic.
http://en.wikipedia.org/wiki/Valence_(psychology)
As a gamer myself, I understand what you're saying about snobbery, though it's not the word I'd choose to use. ;-)
People have different preferences and as such will be affected by situations within the game differently. I suppose I've always thought of this process in a different direction than what you're doing. Rather than the game determining how you should be reacting/feeling, it simply reads what changes occur and adapts to that. Of course designers could choose to attempt to induce a certain emotion at certain times, and they may or may not succeed. But as a general rule the system should attempt to adapt to you, not the other way around.
With regards to valence this means that, for my game in specific, if you are about to win and arousal is going up, the system will assume that that is a positive reaction. With machine learning it could learn differently, should the player insist on feeling stressed at this stage. And if the player wishes for the system to never work properly they could then proceed to randomise they're reactions, providing they are in that good control of they're bodily functions. This is entirely possible, just like it's possible to beat a lie detector, but it's certainly not easy without practise.
Unfortunately I don't know of any Movie experiments that are similar to my experiments, I have semi been on the look out for a couple of years now. I thought about using the drama curve of films in my project, but as my game lacks a storyline, and without one it's tricky to achieve, I shelfed this idea. Still think that would have been really interesting though!
I agree that after a pause the system would have to reset somehow, though I think in a lot of games this could be achieved behind the scenes, whilst play continued. It could mean that the game would delay the appearance of an event which might trigger an emotional response until after recalibration, or something similar. If this was not an option, perhaps the game could get away with not being adaptive during this phase. But if there was no other option, I suppose the boring reset would have to be utilised.
The game I'm talking about will always be one to be used in uncontrolled environments. Controlled environments is a struggle in the sense that people are constantly aware of their surroundings, not being as comfortable and relaxed as they normally would be, leading to considerably less activity in physiology during game play. Having said this, most of my experiments were run in a laboratory setting. :(
Wow, this is an awesome reply! Thanks so much for this, lots here that can go into my thesis ;-)
I think as a game designer you need to focus on how the game is meant to be played. That's not to say that they shouldn't consider how people may play it differently, and account for it, but in the case of Tetris, well if someone can't be bothered moving the blocks to achieve best results, they shouldn't really be playing it. And neither normal games nor adaptive games can really do anything to combat this sort of behaviour. This is not to say that extensive testing should be done to avoid the player destroying the game (getting stuck bugs, glitches in collision detection etc.)! I'm just saying that if the player only wants to wreck havoc then an adaptive game should not be expected to perform any better than a normal game. An adaptive game will attempt to understand the emotional changes in the player, but if he is refusing to play there isn't much the game can do about it.
Regarding the pace issue I believe that most fast pace games are either fairly simple in design, such as tetris or street fighter, or they have waves of fast pace, shooters for instance. Either way, the sensors detect physiological changes as a minimum of 32Hz (32 measurements pr. second), and we know that depending on the sensor it takes up to 4 seconds for the change to take place, and generally it dissipates again after about 6 seconds. Depending on the design on the emotional classification system then, it should not be a problem to determine what triggered the emotional change, should this be required. Not all games need necessarily care what triggered the emotional change.
Though my dream is for these systems to be user independent (which mine is, simple though it may be), I appreciate that allowing the game to learn as it goes along will most definitely benefit the classifier, allowing for more accurate detections, and thus adaptations. However, this requires that each person who ever plays the game has they're own profile, one can never share (like we're currently doing on DJ Hero, playing one song each.. :P). Whether to use machine learning as part of the classifier algorithm really would depend on the individual game, what the designers are trying to achieve etc.
Your ethical observation is astute, it is invasive. However, from my own experiments I find that very few people said they would not consider using such a system if it was affordable, due to invasion of privacy. This is of course a choice, and I'm sure there are people out there who would choose to not play such a game, but I think the majority wouldn't worry about it. Although I agree that it is invasive, I do not agree with your reasoning for it. I suppose it depends on the system, but certainly my own system is not 'monitoring' you emotional states in any ominous way. It simply looks for a change, up or down in arousal, attempts to understand it within the context of the game, and then adapts to it. It does not require a specific emotional state at any one time, it does not expect any states, or changes. The player is free to feel whatever they want to feel, and act however they want to act. Additionally once the change has been determined and adapted to it is not stored in the system, it does not keep tract of your 'emotional journey'. Having said that, should the player wish to, they could attempt to control they bodily functions so as to control the game using physiology as input. The way I look at this though is that if that's what they want to do, that's kinda cool. They choose to use their body, consciously, as an input device to the game. Funky! :)
Hi guys,
Sorry about my recent lack of posts. This is partly due to the fact that I’m only a student 50% of my time, but mostly that I found blogging about this adaptive games stuff really tricky. However, I do need to do this, so I’m taking back up now. I’ve thought about how best to do this, and I’m not sure I’ve come up with a good answer, but at least I have formulated some form of strategy.. We’ll have to see how it pans out! :P My new strategy is based on only making one point per post, which I hope will encourage more of a discussion on that one point at a time, and it should also keep my posts shorter. I appreciate that as little time I have to write these posts, you guys have even less time to read and comment on them!
So without further ado, here’s today’s point:
I’m trying to establish a set of guidelines regarding how to ensure appropriateness of adaptations, based on player emotions, to the game play. Today I’m considering this with respect to the storyline. In some games it may well be not just appropriate but downright exciting to adapt the storyline itself to the emotions of the player. Games such as Fable II and Fallout 3 could benefit from such adaptations, allowing the player to experience a new story every time they played through the game. This would also increase the life span of the games, as the replay value would increase dramatically. Unfortunately, adapting the storyline itself is tremendously difficult, and has yet (to my knowledge) to be done successfully (based on emotions or not).
Do you guys know of any games that does this successfully, or games that do something similar, hack it somehow?
What do you think about the concept of adapting the storyline to player’s emotion? Or adapting any part of the game to the emotions of the player?
Until next time!
Phew
Appropriateness of Adaptation
There are lots and lots of subtopics to think about here!
For me, one of the biggest questions is the following: Is this dependent on game genre, game pace, or style of game play?
I hope that over the coming posts you’ll understand why I pose this question.
The world of computer games is both big and diverse, which suggests that adapting to user emotions may not be appropriate for all games, or indeed in all situations.
Let’s consider single player vs. multiplayer. In a single player situation the environment around the player can adapt to that one user. However, in a multiplayer game, where the players are on opposite teams the environment would have to adapt to two contradicting states. Is this feasible, and if so, how would you do it?
In single player mode the AI of potential monsters can be adapted to the player's emotions, whereas in a multiplayer versus style game, the game cannot adapt one of the player's capabilities. Even attempting to steer the progress of the game through changing luck levels for the players is not advised. This could benefit one player, but the other would end up feeling cheated. This is an ethical issue, one of many. I will attempt to discuss ethics in later posts.
Moving on from single vs. multiplayer there is the question of style of game. I say style of game, because at the moment I'm not sure whether it is genre dependent or dependent on pace or whether the game play is about solving a puzzle, or killing some monster/other player's avatar say. Casual games, such as the game I've made, I think can greatly benefit from emotion detection and adaptation provided it's fast pace.
Consider a casual game such as Frozzd http://www.yoyogames.com/games/show/20523. In this game you "jump from planet to planet as you guide the Mubbly creatures, and use them as an army to defeat the Frozzd." This is an amazing casual game by the way! Definitely worth a try!
The game is not extremely fast pace; you can take your time running and jumping between planets. Having said that, if you encounter the Frozzd you need to be ready, and then things start happening fairly quickly. I think adding emotional adaptations to this game would benefit it as it would differ each time you played it, and in addition it would give you a sense of achievement on each level. More experienced players could then be made to feel challenged from the get go, and noobs could be allowed to finish the game (not necessarily without dying a few times, we’re not talking make it dead easy here..)
On the other hand, consider Mah Jong. I suppose this is also a casual game, but it is a totally different style. Mah Jong is more like a slow card game, matching pairs to make them disappear.
Playing Mah Jong you may well experience different emotions, however because the game play is slow, and it's a game based on thought and careful consideration, the physiological changes are likely to be so slow and small that they could just as well be because of something totally unrelated to the game (e.g. someone comes in to the room and tells you of some good news). This suggests a limitation of the technology and will be discussed in a later post. From a design point of view though, it's hard to see how a game like Mah Jong may benefit from adaptations, or indeed what you may adapt. The blocks are all laid out at the start of the game. As two and two vanish it depends on your own choices whether you will make it or not. In fact, if the game was adaptive and changed certain blocks (it would have to be hidden blocks, or the player would see it changing, which could lead to frustration, or at least boredom if they could see the 'cheating' taking place), the system could potentially change the outcome of the game in a negative fashion by messing up a winning strategy.
This leads me to think it’s not related to the genre of the game so much as pace and/or style of game play. What do you think?
Hi again,
I guess I forgot that most of you out there don't have a clue about what I've been doing or how my system works... Sorry about that! :P
Re how physiology varies from person to person: My system is user independent, which means anyone can use it without training the system first (ish, I train the system for 1 minute pr person, that's it..). Emotions are far from easy to read, and the emotional states my system responds to are not labelled as 'happy', 'bored', 'stressed' etc, but rather are measured as a two dimensional state. The two dimensions are arousal (not sexual, but rather how much 'strength' an emotion is felt with) and valence, which is a happiness scale. To explain with examples, a person who is sad would have low valence (unhappy) and low arousal. Someone who was furious would have low valence, and high arousal.
My system then determines arousal from physiology, and valence from gaming context. So the system uses a threshold to determine a significant change in physiology and then messages the game which checks gaming context and then determines how to adapt.
Still following?
I can re-explain any of this is this crash course is too dense!
The threshold is determined for each person separately. That's what that minute of training does at the start, determines the initial threshold. The threshold then changes throughout the game session, and is dependent on the player's physiology.
In terms of stress that leads to better pay-off the game context should be able to determine whether it is 'good' stress or 'bad' stress. Bad stress I define as when the player no longer feels like she can cope with what's going on. Up until that point you have good stress. However, this specific point is very interesting, and I believe a lot of different developers would have their own take on this. Also, it probably depends on the genre, and game style, not to mention the specific story. My system is very simplistic in the way it deals with this sort of thing, and so it does not plan ahead or know what's about to come. If the game has been designed to arouse a certain level of stress only to majestically resolve it in some climax, then that system should probably allow the player to be stressed through that phase of the game...
Whether the player would have the option to turn on/off certain state recognition would depend on the system design as well as the developers and what they want to achieve. With my system this is not possible, as it only detects significant changes in physiology. I suppose it would have been possible to give the player some options on which adaptive rules could be triggered, e.g. don't change my avatar's speed, but the system would still detect the changes that would normally trigger this change. A different system design could allow for it though, a system using neural networks for instance.
Wow, the next question is a REALLY interesting one! What happens during pause? Well, obviously they have to be allowed to pause the game. Whether the system keeps reading whilst during pause I think would be entirely up to the developers. They could not however assume that the player stays connected to the sensors during the pause, and so could not use these readings once the game starts up again. The system would also have to allow for drastic changes in physiology after a pause, which may or may not be related to a new emotional state. It could be something so simple as the player washed their hands in hot/cold water, or that they had to pop outside for something, or any number of things really. On the other hand perhaps the pause came about because someone came in and started yelling at the player. After an argument the physiology would be quite different, as is the emotional state. So, how should a game deal with this? I have to admit this is something I have never thought about before, and I don't think I have a good answer...not yet anyway! I suspect it would be somewhat determined by the style of game, if there is no storyline it may not matter much. My system would simply calculate a new 'initial' threshold and take it from there, sort of do a re-start of the recogniser. But for most games I think it would matter and my solution would be far from adequate. Do you have any ideas?
And now for my next blog post.... :)
Hi,
I’m trying to develop a set of guidelines, a starting point for debate if you like, regarding how to develop emotionally adaptive computer games for my PhD. The concept behind such games is very simple; keep the player more entertained, for longer. Should she get bored whilst playing, introduce some new and fun elements to the game to heighten her interest. If she is getting too stressed to enjoy playing the game, make the game calm down a little, allowing her to relax and enjoy the experience. As part of my PhD project I have already developed such a game. It uses physiology in conjunction with gaming context to determine the player’s changing emotional state, and adapts accordingly. The game I’ve developed is called TEDDI (Transient Emotion Detecting Designed Interface), and is a Minesweeper style game with some role playing game elements introduced. Think PuzzleQuest, but with Minesweeper, and two boards rather than just the one.
The reason I’m starting this blog is so that all you gamers out there can help me develop my set of guidelines. I’m really looking for your input, any thoughts you may have regarding the big picture of this, or more specifically on the topics of a particular post. Any thoughts/ideas that end up in my thesis will be referenced appropriately, I’m not out to steal your ideas! However, getting expert gamers thoughts will increase the credibility of my work, so I really need you guys!
This post is really only to introduce my blog, more specifics will come later. I’ll probably update this a few times a week from now on. If you have any questions, put them out there, and I’ll try my best to answer. If I don’t have the answer, perhaps someone else does, or perhaps it’s a point we should discuss!
See you next time!
Irene
Happy Birthday!
Hope you get cake in the office today!! :D
2 cents is like 1.3 shiny British pennies. I could travel back in time, get a halfpenny, but then Giant Bomb wouldn't exist! :( We certainly don't want that! So here is my 2p, grossly overpaying and I should therefore win by default..
Log in to comment