[Air-L] Emotion detection and character profiling - validity outside of context?
Veronika Thiel
vt at algorithmwatch.org
Fri Sep 6 02:46:50 PDT 2019
Deare Sally and all,
fascinating conversation about this topic. I am not an academic, but
am professionally always on the lookout for scientific debates around
emotional analysis and psychological testing.
May I slightly hijack this thread to ask if there is a consensus
around context v single word analysis. There is a company called
Precire in Germany (where I am currently based) that claims to be able
to detect a person's personality based on a 15 minute speech sample
about any topic, so independent of context and based on individual
words.
My question: can you deduce personality from a conversation regardless
of the topic (say, you talk about an argument with your neighbour and
the test may well infer that you're a stressed / anxious person,
whereas you talk about your last holiday, then the test may describe
you as relaxed).
This is on the cross line between emotion detection and character
analysis. My understanding/argument is that these tests are generally
not suitable for use in an everyday setting (whereas they may well
support diagnoses of psychological problems/help in therapies), and
that analysis outside of context should be disregarded.
If anyone can direct me to studies discussing this in detail, I'd be
very grateful - the literature is vast and therefore it's difficult to
know who the authorities are in this field and what keywords to search
for.
Please feel free to contact me directly as well.
Thanks and best,
Veronika
Quoting "Dr. S.A. Applin" <sally at sally.com>:
> Dear Charles (and List),
>
> I see this as an ethics issue.
>
> How reliable are “emotion analysis” tools? How would outcomes from
> them be used?
>
> As you say, there is a lack of clarity in some in terms of
> “explaining emotional categories.” To me, this signals (along with
> obvious knowledge about the limitations and problems with
> algorithms), that there is opportunity here to be very, very, very
> wrong about people’s opinions, and any algorithmically interpreted
> “emotional” state.
>
> For example, how would one interpret or finesse “frustration,” vs
> “anger”? The written word is contained within a language. Not all
> commenters will be native speakers to that language, and not all
> native speakers have the language tools required (even within their
> own language) to adequately express themselves, even in the best of
> times. What makes anyone think an algorithm would do better at this
> than a human trained in qualitative methods and with cultural and
> media and language knowledge?
>
> There is way too much margin of potential error here for this to be
> automated, or “useful.” It is much more likely that things will be
> assumed incorrectly by limited algorithms in the first place.
>
> Furthermore, does your student see any problem with this exercise?
> That their tool analysis might get it very wrong? That the wrong
> might lead to assumptions or outcomes that are harmful to entities,
> people, governments?
>
> What safeguards are in place for wrong assumptions and outcomes?
>
> Kind regards,
>
> Sally
>
>
>
>
>
> Sally Applin, Ph.D.
> ..........
> Research Fellow
> HRAF Advanced Research Centres (EU), Canterbury
> Centre for Social Anthropology and Computing (CSAC)
> ..........
> Research Associate
> Human Relations Area Files (HRAF)
> Yale University
> ..........
> Associate Editor, IEEE Consumer Electronics Magazine
> Member, IoT Council
> Executive Board Member: The Edward H. and Rosamond B. Spicer Foundation
> ..........
> http://www.posr.org
> http://www.sally.com
> I am based in Silicon Valley
> ..........
> sally at sally.com | 650.339.5236
>
>
>
>> On Sep 5, 2019, at 3:52 AM, Charles M. Ess <c.m.ess at media.uio.no> wrote:
>>
>> Dear colleagues,
>>
>> One of our students is wanting to analyze emotional content in in
>> the comment fields of a major newspaper vis-a-vis specific
>> hot-button issues.
>>
>> She has a good tool (I think) for scrapping the data - but she is
>> stymied over the choice of an emotion analysis tool. She has looked
>> at Senpy (http://senpy.gsi.upm.es/#test) and Twinword
>> <https://www.twinword.com/api/emotion-analysis.php> - the latter
>> seems the most accurate, but it is also expensive.
>> She has recently discovered DepecheMood emotion lexicons (Staiano,
>> J., & Guerini, M. (2014). Depechemood: a lexicon for emotion
>> analysis from crowd-annotated news. arXiv preprint
>> arXiv:1405.1605.) - but this suffers from a lack of clarity in
>> terms of explaining its emotional categories: awe, indifference,
>> sad, amusement , annoyance, joy, fear and anger.
>>
>> For my part, I am entirely clueless. Any suggestions that she
>> might pursue would be greatly appreciated.
>>
>> best,
>> - charles ess
>> --
>> Professor in Media Studies
>> Department of Media and Communication
>> University of Oslo
>> <http://www.hf.uio.no/imk/english/people/aca/charlees/index.html>
>>
>> Postboks 1093
>> Blindern 0317
>> Oslo, Norway
>> c.m.ess at media.uio.no
>> _______________________________________________
>> The Air-L at listserv.aoir.org mailing list
>> is provided by the Association of Internet Researchers http://aoir.org
>> Subscribe, change options or unsubscribe at:
>> http://listserv.aoir.org/listinfo.cgi/air-l-aoir.org
>>
>> Join the Association of Internet Researchers:
>> http://www.aoir.org/
>>
>
> _______________________________________________
> The Air-L at listserv.aoir.org mailing list
> is provided by the Association of Internet Researchers http://aoir.org
> Subscribe, change options or unsubscribe at:
> http://listserv.aoir.org/listinfo.cgi/air-l-aoir.org
>
> Join the Association of Internet Researchers:
> http://www.aoir.org/
--
Veronika Thiel
Senior Researcher
https://algorithmwatch.org/
vt at algorithmwatch.org
Tel.: +49 30 99 40 49 002
AW AlgorithmWatch gGmbH
Bergstr. 22 10115 Berlin
Sitz der Gesellschaft: Oranienstraße 19A, 10999 Berlin Amtsgericht
Berlin Charlottenburg HRB 186522 B Geschäftsführung: Matthias Spielkamp
More information about the Air-L
mailing list