No abstract

Twitter has become, over the last years, a major source of information. Twitter enables its users to send and read short text-based messages called tweets. Users are busy reporting news about what's going around and within their personal. Numerous researchers from various disciplines have examined Twitter, due to the heterogeneity and immense scale of the data. One of the challenging problems is to automatically identify trending topics in real time on Twitter. Trending topics detection in real time is, thus, of high value to journalists, news reporters, analysts, e-marketing specialists, real-time application developers, and social media researchers to understand what is happening, what emergent trending topics are exchanged between people. In this paper, we propose a new approach that discovers many different trending topics from tweets in real time. Our trending topics are detected for a specific geographic town and compared with the top trending topics shown on Twitter. Contrary to Twitter, our proposed approach distinguishes between different terms corresponding to the same trending topic. We exploit the semantic similarity between keywords composing tweets, by unifying them using a tweets thesaurus former created.Each trending topic has a description presented by keywords of ten tweets that are more representative.

No abstract

No abstract

In this paper, we evaluate our automatic text summarization system in multilingual context. We participated in both single document and multi-document summarization tasks of MultiLing 2015 workshop. Our method involves clustering the document sentences into topics using a fuzzy clustering algorithm. Then each sentence is scored according to how well it covers the various topics. This is done using statistical features such as TF, sentence length, etc. Finally, the summary is constructed from the highest scoring sentences, while avoiding overlap between the summary sentences. This makes it language-independent, but we have to afford preprocessed data first (tokenization, stemming, etc.).