Annotating and Identifying Emotions in Text Page: 28
18 p.View a full description of this chapter.
Extracted Text
The following text was automatically extracted from the image on this page using optical character recognition software:
C. Strapparava and R. Mihalcea
Table 4 System results for emotion annotations
Fine Coarse
r Acc. Prec. Rec. Fl
Anger
SWAT 24.51 92.10 12.00 5.00 7.06
UA 23.20 86.40 12.74 21.6 16.03
UPAR7 32.33 93.60 16.67 1.66 3.02
Disgust
SWAT 18.55 97.20 0.00 0.00 -
UA 16.21 97.30 0.00 0.00 -
UPAR7 12.85 95.30 0.00 0.00 -
Fear
SWAT 32.52 84.80 25.00 14.40 18.27
UA 23.15 75.30 16.23 26.27 20.06
UPAR7 44.92 87.90 33.33 2.54 4.72
Joy
SWAT 26.11 80.60 35.41 9.44 14.91
UA 2.35 81.80 40.00 2.22 4.21
UPAR7 22.49 82.20 54.54 6.66 11.87
Sadness
SWAT 38.98 87.70 32.50 11.92 17.44
UA 12.28 88.90 25.00 0.91 1.76
UPAR7 40.98 89.00 48.97 22.02 30.38
Surprise
SWAT 11.82 89.10 11.86 10.93 11.78
UA 7.75 84.60 13.70 16.56 15.00
UPAR7 16.71 88.60 12.12 1.25 2.27CLaC:
This team submitted two systems [3] to the competition: an unsupervised
knowledge-based system (CLaC) and a supervised corpus-based system (CLaC-
NB). Both systems were used for assigning positive/negative and neutral valence
to headlines on the scale [-100,100].
CLaC:
The CLaC system relies on a knowledge-based domain-independent unsupervised
approach to headline valence detection and scoring. The system uses three main
kinds of knowledge: a list of sentiment-bearing words, a list of valence shifters and
a set of rules that define the scope and the result of the combination of sentiment-
bearing words and valence shifters. The unigrams used for sentence/headline classi-
fication were learned from WORDNETdictionary entries. In order to take advantage
of the special properties of WORDNETglosses and relations, we developed a sys-
tem that used the list of human-annotated adjectives from [19] as a seed list and28
Upcoming Pages
Here’s what’s next.
Search Inside
This chapter can be searched. Note: Results may vary based on the legibility of text within the document.
Tools / Downloads
Get a copy of this page or view the extracted text.
Citing and Sharing
Basic information for referencing this web page. We also provide extended guidance on usage rights, references, copying or embedding.
Reference the current page of this Chapter.
Strapparava, Carlo, 1962- & Mihalcea, Rada, 1974-. Annotating and Identifying Emotions in Text, chapter, 2010; [Berlin, Germany]. (https://digital.library.unt.edu/ark:/67531/metadc31010/m1/8/: accessed April 23, 2024), University of North Texas Libraries, UNT Digital Library, https://digital.library.unt.edu; crediting UNT College of Engineering.