![](bg9.png)
produce contextosets from any kind of dialects or
languages, requiring only basic adaptations (e.g. an
adapted tokenizer) as well as large amounts of texts.
To show the usefulness of contextosets, we pro-
posed to measure their effect on SemEval stance de-
tection task. We introduced two baselines: a sen-
timent analyzer, based on SentiWordNet, and a text
classifier, based on a SVM whose feature vector is
constituted of boolean indicators of unigram pres-
ence. In both cases, contextosets increase the global
F
1
measure, even though “sentiment” does not seem
the best approach on this task.
We believe contextosets have a great potential, and
we will continue to explore the possibilities along
both sentimental and statistical approaches. Even
if our sentiment analyzer failed to predict positive
tweets of stance against, we believe it has the po-
tential to tackle this task. For instance, results may
be improved if we enable it to consider the subject
of the tweet to grasp not only the sentiment polar-
ity, but also its target. The learning approach may
be improved if we use contextosets to disambiguate
ambiguous tweets only, and not all of them.
REFERENCES
Anand, P., Walker, M., Abbott, R., Tree, J. E. F., Bowmani,
R., and Minor, M. (2011). Cats rule and dogs drool!:
Classifying stance in online debate. In Proceedings
of the 2nd workshop on computational approaches to
subjectivity and sentiment analysis, pages 1–9. Asso-
ciation for Computational Linguistics.
Andreevskaia, A. and Bergler, S. (2008). When specialists
and generalists work together: Overcoming domain
dependence in sentiment tagging. In ACL, pages 290–
298.
Baccianella, S., Esuli, A., and Sebastiani, F. (2010). Sen-
tiwordnet 3.0: An enhanced lexical resource for sen-
timent analysis and opinion mining. In LREC, vol-
ume 10, pages 2200–2204.
Bradley, M. M. and Lang, P. J. (1999). Affective norms for
english words (anew): Instruction manual and affec-
tive ratings. Technical report.
Cunningham, H., Maynard, D., Bontcheva, K., Tablan,
V., Aswani, N., Roberts, I., Gorrell, G., Funk, A.,
Roberts, A., Damljanovic, D., Heitz, T., Greenwood,
M. A., Saggion, H., Petrak, J., Li, Y., and Peters, W.
(2011). Text Processing with GATE (Version 6).
Feng, Y., Fani, H., Bagheri, E., and Jovanovic, J. (2015).
Lexical semantic relatedness for twitter analytics. In
Tools with Artificial Intelligence (ICTAI), 2015 IEEE
27th International Conference on, pages 202–209.
IEEE.
Fernando, S. and Stevenson, M. (2012). Mapping wordnet
synsets to wikipedia articles. In LREC, pages 590–
596.
Gotti, F., Langlais, P., and Farzindar, A. (2013). Translating
government agencies tweet feeds: Specificities, prob-
lems and (a few) solutions. NAACL 2013, page 80.
Hagberg, A. A., Schult, D. A., and Swart, P. J. (2008).
Exploring network structure, dynamics, and function
using NetworkX. In Proceedings of the 7th Python
in Science Conference (SciPy2008), pages 11–15,
Pasadena, CA USA.
Hasan, K. S. and Ng, V. (2013). Extra-linguistic constraints
on stance recognition in ideological debates. In ACL
(2), pages 816–821.
Hutto, C. J. and Gilbert, E. (2014). Vader: A parsimonious
rule-based model for sentiment analysis of social me-
dia text. In Eighth International AAAI Conference on
Weblogs and Social Media.
Hyungsuk, J., Ploux, S., and Wehrli, E. (2003). Lexical
knowledge representation with contexonyms. In 9th
MT summit Machine Translation, pages 194–201.
Khan, F. H., Bashir, S., and Qamar, U. (2014). Tom: Twitter
opinion mining framework using hybrid classification
scheme. Decision Support Systems, 57:245–257.
Maynard, D., Bontcheva, K., and Rout, D. (2012). Chal-
lenges in developing opinion mining tools for social
media. Proceedings of the@ NLP can u tag# usergen-
eratedcontent, pages 15–22.
Maynard, D. and Funk, A. (2011). Automatic detection
of political opinions in tweets. In The semantic web:
ESWC 2011 workshops, pages 88–99. Springer.
Mikolov, T., Sutskever, I., Chen, K., Corrado, G. S., and
Dean, J. (2013). Distributed representations of words
and phrases and their compositionality. In Advances in
neural information processing systems, pages 3111–
3119.
Miller, G. A. (1995). Wordnet: a lexical database for en-
glish. Communications of the ACM, 38(11):39–41.
Mohammad, S. M., Kiritchenko, S., Sobhani, P., Zhu, X.,
and Cherry, C. (2016). Semeval-2016 task 6: De-
tecting stance in tweets. In Proceedings of the Inter-
national Workshop on Semantic Evaluation, SemEval,
volume 16.
Nakov, P., Kozareva, Z., Ritter, A., Rosenthal, S., Stoyanov,
V., and Wilson, T. (2013). Semeval-2013 task 2: Sen-
timent analysis in twitter.
Owoputi, O., O’Connor, B., Dyer, C., Gimpel, K., Schnei-
der, N., and Smith, N. A. (2013). Improved part-
of-speech tagging for online conversational text with
word clusters. Association for Computational Lin-
guistics.
Pak, A. and Paroubek, P. (2010). Twitter as a corpus for
sentiment analysis and opinion mining. In LREC, vol-
ume 10, pages 1320–1326.
Palla, G., Dernyi, I., Farkas, I., and Vicsek, T. (2005).
Uncovering the overlapping community structure of
complex networks in nature and society. Nature,
435:814–818.
Pang, B. and Lee, L. (2008). Opinion mining and senti-
ment analysis. Foundations and trends in information
retrieval, 2(1-2):1–135.
ICAART 2017 - 9th International Conference on Agents and Artificial Intelligence
140