Semantic Contextualisation of Social Tag-Based Profiles and Item Recommendations

Abstract

Esta es la versión de autor de la comunicación de congreso publicada en: This is an author produced version of a paper published in: Abstract. We present an approach that efficiently identifies the semantic meanings and contexts of social tags within a particular folksonomy, and exploits them to build contextualised tag-based user and item profiles. We apply our approach to a dataset obtained from Delicious social bookmarking system, and evaluate it through two experiments: a user study consisting of manual judgements of tag disambiguation and contextualisation cases, and an offline study measuring the performance of several tag-powered item recommendation algorithms by using contextualised profiles. The results obtained show that our approach is able to accurately determine the actual semantic meanings and contexts of tag annotations, and allow item recommenders to achieve better precision and recall on their predictions.

Semantic Disambiguation and Contextualisation of Social Tags

“…Since the number of clusters and the cluster sizes are quite similar for the strategies, it seems that the tested similarities are able to capture the semantics underlying the tag subgraphs. This has also been observed in experiments we have conducted to evaluate the impact of the different contextualisation strategies on several tag-powered item recommenders [5]. …”

“…Recently, in [5], we have preliminary evaluated our approach with a number of state of the art recommenders [6] on a Delicious dataset, and have obtained 13% to 24% precision/recall improvements by only contextualising 5.3% of the tags available in that dataset. In the study, we have also conducted a manual evaluation of our tag contextualisation approach.…”

“…Some of them are based on the information available in individual profiles, while others draw information from the whole folksonomy. We have implemented several forms of weighting strategies based on the well-known TF, TF-IDF, and BM25 information retrieval models [5].…”

“…We have implemented the algorithmic framework for tag and profile contextualisation described in Sections 2 and 3 in a system called cTag 5 , which consists of a Web application and a Web service. Figure 2 shows a screenshot of cTag Web application.…”

SNARC - An Approach for Aggregating and Recommending Contextualized Social Content

“…To overcome this problem, we align the incoming stream of posts with the set of semantic concepts or keywords that describe the document. There are several approaches and tools like [2,3,5,6] …”