Arabic Event Detection in Social Media

Alsaedi, Nasser; Burnap, Pete

doi:10.1007/978-3-319-18111-0_29

Cited by 32 publications

(19 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, let's compare character of dependencies in Fig. 1 [1] with results of Twitter crawling that were made in [24] and [25]. These works represent the information propagation (twits' volumes) about Abu Dhabi double-crime event (2014) and Sebastian Vettel victory in Formula 1 (2013), respectively.…”

Section: The Comparison With Statistical Processes Known From Eximentioning

confidence: 99%

“…1, b, that discussion was growth inside the society (is more endogenous), being ad initium quasi exogenous. Therefore, it is suddenly that the event of Sebastian's Vettel victory in F1 competitions (2013), studied in [24] is much more endogenous (correlation indexes are 0.62 versus 0.1, respectively), as the attributes of hidden advertisement and publicity hooks are, evidently, were presented during that campaign. It could be concluded from this that used material by [1] in general is correct and could be used for further scientific investigation process.…”

Section: The Comparison With Statistical Processes Known From Eximentioning

confidence: 99%

See 1 more Smart Citation

Development of Basic Concept of Ict Platforms Deployment Strategy for Social Media Marketing Considering Tectonic Theory

Demydov

Baydoun

Beshley

et al. 2020

EUREKA: Physics and Engineering

View full text Add to dashboard Cite

This paper presents authors analytical view on social impacts as targeted advertisement into the network environment using Omori tectonic theory for description the processes of audience response evolution. This could be extremely important and useful in the modern world to realize desirable e-Gov informational policy in the circumstances of hybrid treats emergence that is especially relevant for the informational space and reaching a cyber-supremacy. Some mathematical and algorithmic basics were contributed for narrative description of information and communications technologies (ICT) architectural deployment could be used for outer regulation of audience response character by Social Media Marketing (SMM) principles. That could be performed by controlled distribution of specified digital content that contains respective key phrases, for example social advertisements and analyzing respective feed-backs. Some results of the empiric study of live audience response dependence on controlled impacts are discussed. Election processes data and recent media recordings for preliminary proof of the contributed concept feasibility have been analyzed. There were shown using gathered empiric data sets, that the extent of impacts to targeted audience response intensity could be the subject of outer regulation. The index has been contributed for assessment the efficiency of the impact's propagation inside the audience by calculation of row correlation of keyword occurrence and audience response intensity. The approaches suggested in the article can be useful both for building effective interactive systems of state-society interaction and for detecting manipulative traits when influencing a specific audience.

show abstract

Section: The Comparison With Statistical Processes Known From Eximentioning

confidence: 99%

Section: The Comparison With Statistical Processes Known From Eximentioning

confidence: 99%

Development of Basic Concept of Ict Platforms Deployment Strategy for Social Media Marketing Considering Tectonic Theory

Demydov

Baydoun

Beshley

et al. 2020

EUREKA: Physics and Engineering

View full text Add to dashboard Cite

show abstract

“…The task requires the detection of events over a stream of tweets without prior knowledge on what events to expect and when they might happen. Our definition of an event (given in Section 3.1) is similar to definitions introduced in (McMinn et al 2013); however, we emphasize event significance, which is often neglected in most event definitions (Alsaedi and Burnap 2015;Becker et al 2011;Petrovic et al 2010). An event in our collection is represented as a set of tweets that are relevant to it within a time period surrounding the time of that event.…”

Section: Multi-task Collectionmentioning

confidence: 99%

EveTAR: building a large-scale multi-task test collection over Arabic tweets

et al. 2017

View full text Add to dashboard Cite

This article introduces a new language-independent approach for creating a large-scale high-quality test collection of tweets that supports multiple information retrieval (IR) tasks without running a shared-task campaign. The adopted approach (demonstrated over Arabic tweets) designs the collection around significant (i.e., popular ) events, which enables the development of topics that represent frequent information needs of Twitter users for which rich content exists. That inherently facilitates the support of multiple tasks that generally revolve around events, namely event detection, ad-hoc search, timeline generation, and real-time summarization.The key highlights of the approach include diversifying the judgment pool via interactive search and multiple manually-crafted queries per topic, collecting high-quality annotations via crowd-workers for relevancy and inhouse annotators for novelty, filtering out low-agreement topics and inaccessible tweets, and providing multiple subsets of the collection for better availability. Applying our methodology on Arabic tweets resulted in EveTAR, the first freely-available tweet test collection for multiple IR tasks. EveTAR includes a crawl of 355M Arabic tweets and covers 50 significant events for which about 62K tweets were judged with substantial average inter-annotator agreement (Kappa value of 0.71). We demonstrate the usability of EveTAR by evaluating existing algorithms in the respective tasks. Results indicate that the new collection can support reliable ranking of IR systems that is comparable to similar TREC collections, while providing strong baseline results for future studies over Arabic tweets.This manuscript describes a major extension to an earlier preliminary version published at SIGIR'16 (Almerekhi et al. 2016). Improvements over the preliminary work include providing a much deeper justification of the design choices made during the creation of the collection, extension of the test collection to support two additional tasks, improvements to the judgments collected, providing four subsets of the collection to increase its accessibility and use case scenarios, and running experiments that demonstrate the reliability of the proposed test collection. Improvements to the judgments include filtering out topics with low-agreement among annotators, removal of inaccessible tweets from the document collection, collecting additional relevance judgments to increase the qrels set size, and collecting novelty judgments to allow the collection to support two tasks (timeline generation and real-time summarization).

show abstract

“…Focusing on Arabic data, Alsaedi and Pete [14] train a Naïve Bayes classifier on Arabic tweets to extract events as part of a framework to apply a supervised approach to classify, cluster and summarize events. Worth noting that, this research is the only one available for extracting events from Arabic tweets.…”

Section: B Sentence-level Event Extractionmentioning

confidence: 99%

“…However, research targeting event extraction out of Arabic text is limited [11]- [13] and to the best of our knowledge there is only one concurent research reported on event extraction out of Arabic tweets [14].…”

Section: Introductionmentioning

confidence: 99%