Incremental autoencoders for text streams clustering in social networks

Clustering data streams in order to detect trending topic on social networks is a chal- lenging task that interests the researchers in the big data field. In fact, analyzing such data needs several requirements to be addressed due to their large amount and evolving nature. For this purpose, we propose, in this paper, a new evolving clustering method which can take into account the incremental nature of the data and meet with its principal requirements. Our method explores a deep learning technique to learn incrementally from unlabelled examples generated at high speed which need to be clustered instantly. To evaluate the performance of our method, we have conducted several experiments using the Sanders, HCR and Terr-Attacks datasets.

Preserve Integrity in Realtime Event Summarization

Online text streams such as Twitter are the major information source for users when they are looking for ongoing events. Realtime event summarization aims to generate and update coherent and concise summaries to describe the state of a given event. Due to the enormous volume of continuously coming texts, realtime event summarization has become the de facto tool to facilitate information acquisition. However, there exists a challenging yet unexplored issue in current text summarization techniques: how to preserve the integrity, i.e., the accuracy and consistency of summaries during the update process. The issue is critical since online text stream is dynamic and conflicting information could spread during the event period. For example, conflicting numbers of death and injuries might be reported after an earthquake. Such misleading information should not appear in the earthquake summary at any timestamp. In this article, we present a novel realtime event summarization framework called IAEA (i.e., Integrity-Aware Extractive-Abstractive realtime event summarization). Our key idea is to integrate an inconsistency detection module into a unified extractive–abstractive framework. In each update, important new tweets are first extracted in an extractive module, and the extraction is refined by explicitly detecting inconsistency between new tweets and previous summaries. The extractive module is able to capture the sentence-level attention which is later used by an abstractive module to obtain the word-level attention. Finally, the word-level attention is leveraged to rephrase words. We conduct comprehensive experiments on real-world datasets. To reduce efforts required for building sufficient training data, we also provide automatic labeling steps of which the effectiveness has been empirically verified. Through experiments, we demonstrate that IAEA can generate better summaries with consistent information than state-of-the-art approaches.

Deriving Business Value From Online Data Sources Using Natural Language Processing Techniques

The wealth of information produced over the internet empowers businesses to become data-driven organizations, increasing their ability to predict consumer behavior, take more informed strategic decisions, and remain competitive on the market. However, past research did not identify which online data sources companies should choose to achieve such an objective. This chapter aims to analyse how online news articles, social media messages, and user reviews can be exploited by businesses using natural language processing (NLP) techniques to build business intelligence. NLP techniques assist computers to understand and derive a valuable meaning from human (natural) languages. Following a brief introduction to NLP and a description of how these three text streams differ from each other, the chapter discusses six main factors that can assist businesses in choosing one data source from another. The chapter concludes with future directions towards improving business applications involving NLP techniques.

Human Sentiment and Activity Recognition in Disaster Situations Using Social Media Images Based on Deep Learning

A rapidly increasing growth of social networks and the propensity of users to communicate their physical activities, thoughts, expressions, and viewpoints in text, visual, and audio material have opened up new possibilities and opportunities in sentiment and activity analysis. Although sentiment and activity analysis of text streams has been extensively studied in the literature, it is relatively recent yet challenging to evaluate sentiment and physical activities together from visuals such as photographs and videos. This paper emphasizes human sentiment in a socially crucial field, namely social media disaster/catastrophe analysis, with associated physical activity analysis. We suggest multi-tagging sentiment and associated activity analyzer fused with a a deep human count tracker, a pragmatic technique for multiple object tracking, and count in occluded circumstances with a reduced number of identity switches in disaster-related videos and images. A crowd-sourcing study has been conducted to analyze and annotate human activity and sentiments towards natural disasters and related images in social networks. The crowdsourcing study outcome into a large-scale benchmark dataset with three annotations sets each resolves distinct tasks. The presented analysis and dataset will anchor a baseline for future research in the domain. We believe that the proposed system will contribute to more viable communities by benefiting different stakeholders, such as news broadcasters, emergency relief organizations, and the public in general.