Linked knowledge sources for topic classification of microposts: A semantic graph-based approach

Abstract

Short text messages a.k.a Microposts (e.g. Tweets) have proven to be an effective channel for revealing information about trends and events, ranging from those related to Disaster (e.g. hurricane Sandy) to those related to Violence (e.g. Egyptian revolution). Being informed about such events as they occur could be extremely important to authorities and emergency professionals by allowing such parties to immediately respond.In this work we study the problem of topic classification (TC) of Microposts, which aims to automatically classify short messages based on the subject(s) discussed in them. The accurate TC of Microposts however is a challenging task since the limited number of tokens in a post often implies a lack of sufficient contextual information.In order to provide contextual information to Microposts, we present and evaluate several graph structures surrounding concepts present in linked knowledge sources (KSs). Traditional TC techniques enrich the content of Microposts with features extracted only from the Microposts content. In contrast our approach relies on the generation of different weighted semantic meta-graphs extracted from linked KSs. We introduce a new semantic graph, called category meta-graph. This novel meta-graph provides a more fine grained categorisation of concepts providing a set of novel semantic features. Our findings show that such category meta-graph features effectively improve the performance of a topic classifier of Microposts.Furthermore our goal is also to understand which semantic feature contributes to the performance of a topic classifier. For this reason we propose an approach for automatic estimation of accuracy loss of a topic classifier on new, unseen Microposts. We introduce and evaluate novel topic similarity measures, which capture the similarity between the KS documents and Microposts at a conceptual level, considering the enriched representation of these documents.Extensive evaluation in the context of Emergency Response (ER) and Violence Detection (VD) revealed that our approach outperforms previous approaches using single KS without linked data and Twitter data only up to 31.4% in terms of F1 measure. Our main findings indicate that the new category graph contains useful information for TC and achieves comparable results to previously used semantic graphs. Furthermore our results also indicate that the accuracy of a topic classifier can be accurately predicted using the enhanced text representation, outperforming previous approaches considering content-based similarity measures.

Finding Diachronic Like‐Minded Users

“…Applying topic modeling methods such as LDA and ToT to extract topics from tweets might suffer from the sparsity problem (Sriram et al 2010;Cheng et al 2014), because they are designed for regular documents and not short, noisy, and informal texts like tweets. As suggested in Varga et al (2014), to obtain better topics from Twitter without modifying the standard topic detection methods, we annotate each tweet m 2 M with concepts defined in Wikipedia using an existing semantic annotator. We see each concept as a term in the set W .…”

Neighborhood-user profiling based on perception relationship in the micro-blog scenario

“…Based on clustering the keywords from the electronic academic publications in online service, Tang [21] focuses on extending scientific subject ontology to refine user interest profiling. Varga [22] introduced a new semantic graph, called category meta-graph, to extract a more fine grained categorisation of concepts to provide a set of novel semantic features from short text messages.As the cosine similarity and TF-IDF weighting scheme for terms occurring in news messages are used in most user profiles, Hogenboom [23] extended semantics based weighting techniques, Bing-SF-IDF+, by considering the synset semantic relationships and by employing named entity similarities using Bing page counts, to perform better of F1 than TF-IDF and SF-IDF methods. For the hierarchical semantic structure embedded in the query and the document, Huang [24] used a deep neural network (DNN) to rank a set of documents for a given query and proposed a series of Deep Structured Semantic Models (DSSM) for Web search.…”

Stretching the Life of Twitter Classifiers with Time-Stamped Semantic Graphs

“…Other approaches have incorporated the use of external knowledge sources (KS) to enrich Twitter content. Some of them relying only on KS [10,23,17]; others incorporating semantic features derived from semantic meta graphs [26,3] on supervised settings; and others incorporating DBpedia lexical features on unsupervised classification tasks [2]. However to the best of our knowledge, none of these approaches focused on the epoch-based transfer learning task.…”

“…The incorporation of new event-data to a topic representation leads to a linguistic evolution of a topic, but also to a change on its semantic structure. To the best of our knowledge, none of the existing approaches for topic classification using semantic features [10][3] [26], has focused on the epoch-based transfer learning task. In this work we present a comparison of lexical and semantic features on epoch-based transfer learning tasks.…”