Sentiment-oriented information retrieval (Bisio et al) (2016)
SenticNet is a sentiment-based database for retrieval based on metrics using variations of graded opinions present in various documents.
It has semantics of around 30,000 concepts which assist in opinions mining of huge natural language tasks.
Many algorithms are previously proposed based on lexicon and their associated sentiments
Concept-based approaches inherently cover deeper meaning approach than purely statistical keyword-based techniques. These often analyse sentiments as opinions associated with the text.
SenticNet 3 enables the flow of energy by combining connections of text to related fragments.
Use DBPedia which have 2.6 million entities from Wikipedia
Information converted to RDF triples and then inserted into a graph.
Everything is measured as a quantum of energy.
Measure of pleasantness, attention, sensitivity and aptitude are calculated.
SenticNet software is based on MySQL database interaction with SLAIR, which is C++ based IR software for document processing.
Evaluations were performed
A new fuzzy logic based ranking function for efficient information retrieval system (Gupta et al) (2015)
Vector Space Model for documents
Three Fuzzy Inference Engines (FIS)
1st FIS – term frequency of document, inverse document frequency and number of terms as inputs to 1st FIS, defuzzified value is wd.
2nd FIS — term frequency of query, inverse document frequency and number of terms in query as inputs to 1st FIS, defuzzified value is wq.
The 3rd FIS takes input as outputs of above two FIS which is wd and wq. This model is build with expert defined rules and the output is relevance score of the document for that query.
Evaluations on CACM and CISI datasets.
An enhanced multi-view fuzzy information retrieval model based on linguistics (Attia et al) (2014)
Semantic fuzzy retrieval model.
Multi domain fuzzy ontology.
This ontology have linguistic based query processing.
Bisio, F., Meda, C., Gastaldo, P., Zunino, R., & Cambria, E. (2016). Sentiment-oriented information retrieval: Affective analysis of documents based on the senticnet framework. Sentiment Analysis and Ontology Engineering: An Environment of Computational Intelligence, 175-197.
Attia, Z. E., Gadallah, A. M., & Hefny, H. M. (2014). An enhanced multi-view fuzzy information retrieval model based on linguistics. IERI Procedia, 7, 90-95.
Gupta, Y., Saini, A., & Saxena, A. K. (2015). A new fuzzy logic based ranking function for efficient information retrieval system. Expert Systems with Applications, 42(3), 1223-1234.
Hi, Apart from profession, I have inherent interest in writing especially about Global Issues of Concern, fiction blogs, poems, stories, doing painting, cooking, photography, music to mention a few! And most important on this website you can find my suggestions to latest problems, views and ideas, my poems, stories, novels, some comments, proposals, blogs, personal experiences and occasionally very short glimpses of my research work as well.
View more posts