![](bg6.png)
parallelize complex analysis operators such as filter,
join and aggregate (Sridhar et al., 2009).
In order to speed-up costly operations within the
inner i-SLOD datasets, additional indexing
mechanisms can be applied. For example, instead of
performing a join between the opinion atom and the
indicator datasets every time a user asks a query
involving such datasets, we can build an index that
associates each opinion atom with its indicators.
More challenging is however, to efficiently perform
BI operations involving external datasets, as we do
not have control over the external sources.
On the other hand, the semantics introduced by
the linked data flavour of the i-SLOD also require
new scalable, distributed reasoning techniques able
to efficiently compute new inferences so that they
can be used in the analysis process.
5 CONCLUSIONS
We have presented i-SLOD, a proposal for a data
infrastructure of open linked sentiment data. Its
purpose is to facilitate the massive analysis of
sentiment data by exploiting the ever-increasing
amount of publicly available open linked data.
The i-SLOD components are designed to
describe all necessary information for opinion
analysis (products/services, features/aspects, and
opinion indicators, reviews and facts), and also to
incorporate the functionality required to perform
massive opinion analysis: the extraction of opinion
facts from text reviews, and the linkage of opinion
data to other datasets, using semantic annotation as a
key enabling technology.
This allows the exploitation of opinion-related
dimensions of analysis that are out of reach for
traditional BI applications, thus allowing the
incorporation of crucial strategic information.
ACKNOWLEDGEMENTS
This work has been partially funded by the
“Ministerio de Economía y Competitividad” with
contract number TIN2011-24147.
REFERENCES
Cambria, E., Song, Y., Wang, H., Howard, N. (2013).
Semantic Multi-Dimensional Scaling for Open-
Domain Sentiment Analysis. IEEE Intelligent Systems,
DOI: 10.1109/MIS.2012.118.
Dean, J., Ghemawat, S. (2004). Mapreduce: Simplified
data processing on large clusters. OSDI ’04, pages
137–150.
Esuli, A., Sebastiani, F. (2006). SENTIWORDNET: A
Publicly Available Lexical Resource for Opinion
Mining. In Proc. LREC’06, 417-422.
García-Moya, L., Kudama, S., Aramburu, M.J., Berlanga,
R. (2013a). Storing and analysing voice of the market
data in the corporate data warehouse. Information
Systems Frontiers, 1-19, DOI: 10.1007/s10796-012-
9400-y.
García-Moya., Anaya-Sánchez, H., Berlanga, R. (2013b).
A Language Model Approach for Retrieving Product
Features and Opinions from Customer Reviews, IEEE
Intelligent Systems, DOI: 10.1109/MIS.2013.37.
Heath, T., Bizer, C. (2011). Linked Data: Evolving the
Web into a Global Data Space. Morgan & Claypool,
San Rafael, CA, 1st Edition.
Liu, B., (2012). Sentiment Analysis and Opinion Mining,
Morgan & Claypool Publishers.
Lu, Y., Castellanos, M., Dayal, U., Zhai, C. X. (2011).
Automatic construction of a context-aware sentiment
lexicon: an optimization approach. WWW 2011, 347-
356.
Mendes, P., Jakob, M., García-Silva, A., Bizer, C., 2011.
DBpedia spotlight: shedding light on the web of
documents. In Proc. of I-Semantics '11.
Polanyi. L, Zaenen, A. 2006. Contextual valence shifters.
Computing Attitude and Affect in Text: Theory and
Applications: The Information Retrieval Series
Volume 20, 1-10, doi: 10.1007/1-4020-4102-0_1.
Sridhar, R., Ravindra, P., Anyanwu, K. (2009). RAPID:
Enabling Scalable Ad-Hoc Analytics on the Semantic
Web. In Proc.s of ISWC '09, 715-730.
Thelwall, M., Buckley, K., Paltoglou, G. Cai, D., Kappas,
A. (2010). Sentiment strength detection in short
informal text. JASIST, 61(12), 2544–2558.
Westerski, A., Iglesias, C. A. (2011). Exploiting
Structured Linked Data in Enterprise Knowledge
Management Systems. An Idea Management Case
Study. In Proc. EDOCW, 395-403.
i-SLOD:TowardsanInfrastructureforEnablingtheDisseminationandAnalysisofSentimentData
219