Exploiting Higher-level Semantic Information for the Opinion-oriented Summarization of Blogs

Together with the growth of the Web 2.0, people have started more and more to communicate, share ideas and comment in blogs, social networks, forums and review sites. Within this context, new and suitable techniques must be developed for the automatic treatment of the large volume of subjective data, to appropriately summarize the arguments presented therein (e.g. as "in favor" and "against"). This article assesses the impact of exploiting higher-level semantic information such as named entities and IS-A relationships for the automatic summarization of positive and negative opinions in blog threads. We first run a sentiment analyzer (with and without topic detection) and subsequently a summarizer based on a framework drawing on Latent Semantic Analysis. Further on, we employ an annotated corpus and the standard ROUGE scorer to automatically evaluate our approach. We compare the results obtained using different system configurations and discuss the issues involved, proposing a suitable method for tackling this scenario.JRC.DG.G.2-Global security and crisis managemen