Netherlands eScience Center
8 May 2015
View this email in your
browser<http://us8.campaign-archive2.com/?u=a0a563ca342f1949246a9f92f&id=aaa349f832&e=8827c96914>
[https://gallery.mailchimp.com/a0a563ca342f1949246a9f92f/images/ESCIENCE_logo_B_nl_long_cyanblack_Converted_ec00c3.png]
Emotions in film reviews
Social scientists are researching the emotions which films arouse in viewers in
order to better understand the role of media in society and culture. Mapping
the emotions which are aroused by a film could also prove useful for
recommending films which a user might find interesting (like Netflix does, for
example). One challenge when mapping the emotions of viewers is the fact that
it is difficult and expensive to measure these emotions.
eScience Research Engineer Lars Buitinck from the Netherlands eScience Center
measures the emotions which are evoked by films by analyzing amateur film
reviews. In collaboration with communication scientists at the UvA, he has
developed a method for automatically identifying emotions. Buitinck presented
his method during the 37th edition of the international “European Conference on
Information Retrieval” in Vienna.
Multiple emotions within a single sentence
Previous research into emotion recognition mainly focused on recognizing
emotions at sentence level and was limited to a binary distinction: a sentence
will either express a positive or a negative emotion. Buitinck's new method can
identify multiple emotions within a single sentence. The method uses
statistical patterns in word usage in order to identify expressed emotions and
also takes correlations between human emotions into account (which emotions
occur together relatively frequently?).
Text analysis of film reviews on the internet
In order to develop this method, the researchers picked film reviews from the
internet in which they manually identified expressed emotions (which words
express an emotion?) and then classified them (which emotion is being
expressed?). Using this collection of reviews and emotions, the next task was
to develop an algorithm which was capable of detecting the emotions in reviews
as effectively as the communication scientists themselves. Buitinck's algorithm
was able to detect the same emotions as the scientists in 85% of cases.
Data set
As well as presenting two new algorithms for detecting multiple expressed
emotions within a sentence, Buitinck has also published the data set of reviews
and identified emotions so that other scientists can use this information.
Access the data set
here<http://eScienceCenter.us8.list-manage1.com/track/click?u=a0a563ca342f1949246a9f92f&id=fb8a84b980&e=8827c96914>
Publication details
Buitinck L, van Amerongen J, Tan E, de Rijke M. 2015. Multi-emotion detection
in user-generated
reviews<http://eScienceCenter.us8.list-manage1.com/track/click?u=a0a563ca342f1949246a9f92f&id=4b372ae40a&e=8827c96914>.<http://eScienceCenter.us8.list-manage.com/track/click?u=a0a563ca342f1949246a9f92f&id=9a93b81651&e=8827c96914>
ECIR 2015: 37th European Conference on Information Retrieval.
Article Source: Informatics Institute University of
Amsterdam<http://eScienceCenter.us8.list-manage.com/track/click?u=a0a563ca342f1949246a9f92f&id=f4035480a7&e=8827c96914>
About NLeSC
NLeSC is the national expertise center for the development and application of
domain overarching software and methods for the scientific community. NLeSC
develops crucial bridges between increasingly complex modern e-infrastructures
and the growing demands and ambitions of scientists from across all disciplines.
NLeSC funds and participates in multidisciplinary projects, with academia and
industry, with optimized data-handling, efficient computing and big-data
analytics at their core.
NLeSC is a joint initiative of the Dutch national research council (NWO) and
the Dutch organization for ICT in higher education and research (SURF).
www.eScienceCenter.nl<http://eScienceCenter.us8.list-manage.com/track/click?u=a0a563ca342f1949246a9f92f&id=fc8c8fce8f&e=8827c96914>
Copyright © 2015 Netherlands eScience Center, All rights reserved.
This is a forwarded newsletter.
Our mailing address is:
Netherlands eScience Center
Science Park 140
Amsterdam, 1098 XG
Netherlands
Add us to your address
book<http://eScienceCenter.us8.list-manage.com/vcard?u=a0a563ca342f1949246a9f92f&id=203e1c295c>
unsubscribe from this
list<http://eScienceCenter.us8.list-manage.com/unsubscribe?u=a0a563ca342f1949246a9f92f&id=203e1c295c&e=8827c96914&c=aaa349f832>
update subscription
preferences<http://eScienceCenter.us8.list-manage.com/profile?u=a0a563ca342f1949246a9f92f&id=203e1c295c&e=8827c96914>
[Email Marketing Powered by
MailChimp]<http://www.mailchimp.com/monkey-rewards/?utm_source=freemium_newsletter&utm_medium=email&utm_campaign=monkey_rewards&aid=a0a563ca342f1949246a9f92f&afl=1>
