[Aleader-dev] Re: direction

[William L. Jarrold]

On Tue, 5 Aug 2003, Joshua N Pritikin wrote:

> [I am aware of your limited time.  I don't expect you to acknowledge
> everything I wrote in this email.  I am keeping track of any issues
> which I feel are unresolved so I can feed them back to you later.
>
> For example, over the last few days I have made an effort to better
> separate the science & philosophy portions of Aleader.  Eventually
> (not now!) I want to revisit whether the new organization hides
> the philosophy sufficiently well.]
>
> On Mon, Aug 04, 2003 at 08:49:53PM -0500, William L. Jarrold wrote:
> > I am finally attaching my comments on the tutorial.  They  way
> > they are written is sort of halphharzed.  I first only
> > put new stuff by commenting it out with % and putting at
> > WLJ at the start of it.  Then I did a big comment blurb with
> > WLJ.  Might be best to respond to that via email discussion
> > rather than attachment.  Then I went back and changed a few
> > lines of the original text without adding any WLJ indicators figuring
> > you can use a diff like tool to find 'em easy.
>
> The best way is just to change stuff without putting in any %WLJ
> marker.  Diff (or emacs's emerge) works great.
>
> I see a lot of uncontroversial edits, such as:
>

<...>

>
> > Both "Master Yupas" are distinct from one another...One involves
> > a set of collegial regard and the other is more like, yay, papa is back.
> > The former emotions depicted are more adult in tone, the latter more
> > childlike in tone.
>
> Agreed.
>
> In any classification scheme, some variation is unavoidable.
> The challenge is to see how well we can minimize the variation.
>
> In this particular case, I don't have any idea how to do better.
> Subjectively, I find both "Master Yupa"s similar enough.  I do not
> feel urgent motivation to further distinguish them.

Hmm. Well, they felt different to me.  Different enough to deserve
different labels.

Seems to me that this whole thing is like classifying snoflakes.  There
will be numerous categories at many different levels of granularity.
At bottom, every snowflake is different.  What may seem like a salient
level of granularity to you might not seem that way to others.  And my
reaction to the two "Master Yupas" anecdotally supports this claim.  But,
the experiment we are talking about seems like a good way to test the
claim that a given level of granularity works to such and thus a level.

It might be worthwhile to throw in pairs that contain the identical piece
of film.  What also might be worthwhile is to find two films, one a remake
of the other.  How similar are corresonding scences?  How does this
similarity compare to scenes from the same category?  (If you could toss
this paragraph into the research proposal that would be great...even if
you disagree with it, it is useful to stimulate ideas about what we might
do or not do instead)

>
> > o I did not really get passed a thorough checkout of "celebrate
> > presence", i.e. Item #31.  However, I did a random leap and ended up
> > looking at "You think I'm afraid of you big fuck?" from Goodwill
> > Hunting.  This appeared to be classified as admiration (there was a box
> > checked next to "[+] admires [0].").
>
> Perhaps it seems strange to classify this situation as "admires"?
> "Admires" is actually a _general_ category.

Sure.  I agree that if a category is labeled "Admires" then (assuming
lables kinda sorta reflect what the categories mean) it is a little more
coarse than the rest of Aleader.  It might be good to have a list of
examples of categories that seem too coarse and a list that seems too
fine.

Ah, ding!  Finally.  There is the field of cluster analysis.  Way cool
stuff.  I *think* it is called cluster analysis.  Basically you take scads
of similarity ratings involving pairs of items.  Then a computer
figures out how to cluster them nicely....So, we might even take
pairs of random film segments and see what happens.  This kind of thing
*must* have been done in the literature.  We must scour _Cognition and
Emotion_

>
> This situation also classifies to the _specific_ category
> "haughty / arrogant" (which is a sub-type of admires).
>

I think we may have discussed this but haughty and arrogant does not
seem like a sub type of admires unless admires includes self-admiration.
Haughtiness and arrogance seem to arise in people who admire themselves.
Yes, no, maybe?

> One more comment: I have not put much effort into translating
> Aleader's affective assessment in idiomatic, common-sense
> English.  This is one of the many reasons why I request people
> to stop reading my explanation and start watching film clips.

I might be wrong here, but I *think* I appreciate the difficulty in
labeling certain categories.  Words can be v v misleading.  In Cyc there
were like 27 versions of the "in" relation.  There was a time when I
thought they should be named in-7, in-3, in-14 etc so as to force people
to grok the terms in their full richness and subtlty and prevent them
from prejudging meaning based on some simple English label.  Result: the
relations were never used by other ontologists and they complained
bitterly until I renamed them stuff like in-Lodged, in-ImmersedPartially,
in-ContGeneric etc..

>
> > okay, well, basically I think I get it.   ...
> > ... there is some similarity.  Sure, there is a happy feeling
> > felt by certain characters in all of those scenes.
> > ...
> > So far, the chief value of your system seems to me to be able to
> > provide a vivid and reliable depictor of emotions.
>
> Great!  Now I won't have to run around in circles trying to verbally
> explain what you have now seen & quickly absorbed first-hand.
>
> If we publish an article, I guess we should "strongly recommend"
> that readers try out the CD?

Oh I guess.  I'm just not into that aspect of it as much as you are.
Keep after me and we'll see what happens.  The computer lab that lends
me computers is closed for a while so I'm not able to play with Aleader.

>
> For those readers who don't try the CD, how much of an attempt
> should we make to verbally explain what is on the CD?  Perhaps
> such a description should go in an appendix or something?

I personal growth people need to see it more than the researchers.
But for them, you won't have much of a chance to market it other than in
print.....I don't think we need to answer your question exactly right now.
THe much much bigger task is to build something that people will
use.  Best prospect I think is to focus on elementary school kiddos,
especially those with autism/asperger's needing social skills and empathy
training.

>
> > Maybe, if you replace your categories with OCC categories and/or Roseman
> > categories you will get more attention from the academic community.
>
> I certainly want to compare/constrast with OCC & Roseman.  In fact, I
> got a copy of Roseman96 today.  Sorry it took so long.  I am looking
> forward to reading it.  However, I am not willing to dump the Aleader
> model.  Perhaps I am stubborn or irrational about this, but I continue
> to believe that Aleader offers a more precise affective model than any
> other existing model.  Obviously, this belief does not rest on being
> well-read.  It rests on a long inner struggle and deep introspection.
> I will offer some comments on Roseman soon though, in any case.
>
> In your first email, you suggested that I narrow the scope of my
> research.  I agree that I am trying to do something "too big."
> However, I don't see a problem with that.  I don't have a deadline.
> We can proceed in small, manageable steps.  Be involved as much as
> you want.  I appreciate your feedback very much.

Right.  In Research World, I'm not against eventually ending up with
something as complex as Aleader.  But to get there we first need to
scientifically validate principles such as  "If you get what you want you
feel happy.  If you don't get what you want then you feel sad."
Validating a model like that is one of the first 100 baby steps to take.

>
> > One important
> > question is, is there more heterogenetiy between categories than within
> > categories?  One way you could test this is ask people to view pairs of
> > scenes and rate their affective similarity on a scale of 1-5.
>
> That's a great idea!  Why didn't I think of that?  Here is an instance
> where your broad awareness of the field of cognitive psychology really
> helps me out.
>
> I have already done most of the work to automate this type of test.
> I will get busy and make a few more preparatory changes to the software.
> Perhaps within a week, we'll be ready (software-wise) to get started
> testing human subjects.

Cool.  Howz that gone?

>
> > o It would be interesting to apply different types of text understanding
> > and/or statistical NLP to the scripts you have provided.  If it's
> > inferences could be sync'd up to different film clips and its inferences
> > compared to human's inferences watching (reading?) the same film
> > (script), now we are getting something quite interesting.
> > Specifically, by comparing affective judgements in each of these three
> > conditions.
>
> That does sound very exciting.  It also sounds like something that
> requires big databases and more computing power than I have at
> present.
>

I thought I answered this.  I don't think it is that compute intensive.

> On the other hand, I do want to collect these more ambitious research
> ideas.  Who knows, semi-automated emotional analysis of complete films
> may be of practical value to Hollywood studios.
>
> Personally I am happy to begin with an investigation of the question
> you raise above, "is there more heterogeneity between categories than
> within categories?".  The test will require little effort to
> administer.  Statistical analysis is straightforward.  There is lots
> of precedent in the published literature (can you suggest a
> particularly good article which I can use as a model?).

Alas, NO!  We must search the literatute before really starting in
earnest....Actually, there is a paper kinda like this...Ask me again
when I am at home I can dig through my files and try to find it.

> We could even
> limit the scope of the test to the 10 easy categories in the "getting
> started" guide (maybe, this choice has pros & cons).  It should be
> relatively easy.  What do you think?

The problem is that one could critique the study and say, Of course you
found the inter category emotions to be more similar than the cross
category ones.  That's because you picked categories that were radically
different.  Maybe this is not a big problem.  I should try to meet with
my advisor and she what she says.

>
> A simple article like this may be a necessary pre-cursor to a big NLP &
> inferencing project anyway.  Isn't it?

Probably.  But it would be easy to see how accurate liwc was in rating a
given section of the script.  Do you have the scripts in free text form?
We could feed 'em to liwc chunk by chucnk right away.  Would the
count of happy (or whatever category) words vary interestingly as a
function of chunk?

(Btw, how did you get the scripts?)

>
> > I am still quite unfamiliar with your theory.
>
> Even so, I want to decide a course of action.  Unless you come up with
> something better, I am going to plan my time according to the aim of
> publishing an article addressing the question: "is there more
> heterogeneity between categories than within categories?"

Okay.  But you run the risk of wasting your energy.  There is a decent
chance I'll change my mind after ruminating more, asking Diane (my
adivosr), researching the literature.

>
> I guess I need to write a research proposal now?  Perhaps a one page
> outline giving an overview of what we have, what we want to do with
> it, and what we resources we need?

Good.  You are more of a man of action than me.

>
> I hope you can guide me through the process and perhaps help with
> corralling human subjects.  I _may_ be able to find English speaking
> human subjects here in Nashik too.  Perhaps it would add something to
> use human subjects from two different countries?

I think we've emailed about this subject.

>
> I hope you find time to explore Aleader in a bit more depth.  Here are
> my predictions about what you will find:
>
> + The categories are more robust than you thought initially.
>
> + You will appreciate the elegance and computability of the model.
>
> + You will see how the model can be extended or scaled up.
>
> + Simultaneous with your growing appreciation of the model, you will
> begin to feel that most people will need some training to go beyond
> the ten easy categories.  I think this is a rather sticky problem.
> I look forward to hearing your opinion about it.

Well, we shall see.

Bill

>
> --
> .. Sensual .. Perceptual .. Cognitive .. Emotional .. Oh My!
>