Social networking trends and dynamics detection via a cloud-based framework design

Vakali, Athena; Γιάτσογλου, Μαρία; Antaris, Stefanos

doi:10.1145/2187980.2188263

Cited by 22 publications

(21 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Current data mining (such as clustering) approaches focus on detecting (e.g., in Twitter): (i) clusters of users densely associated via follower or message links, or (ii) groups of tweets using text mining techniques such as exploiting common word co-occurrences [3] .…”

Section: Micro-blogosphere Trends Detection: Status and Challengesmentioning

confidence: 99%

“…To deal with noise, TwitterStand also filters out tweets that are unrelated to news via a classification method based on the Naïve Bayes Classifier. After that, the tweets are clustered with an online method that holds many similarities to the one followed in Cloud4Trends application [3] . In particular, TwitterStand's algorithm extracts TF-IDF feature vectors for the tweets and clusters and performs clustering based on their similarity, while also incorporating the temporal dimension in the clustering process in the same way as Cloud4Trends does.…”

Section: Mining For Trend Analysismentioning

confidence: 99%

“…Several text preprocessing methodologies (e.g., emoticon identification, acronyms recognition, etc.) are proposed as vital for the refinement of the text content and the improvement of the clustering approach [3] .…”

Section: Challenges In Crowdsourced Trend Analysismentioning

confidence: 99%

“…It leverages on Cloud4Trends, a framework proposed by the authors to enable online identification of trends dynamics, using Twitter and the Blogosphere [3] . It is important to notice that some commercially available products have focused on offering trend analytics solutions, with two examples shown here [17,18] .…”

Section: Leveraging Cloud4trends For Social Text Dynamics Detectionmentioning

confidence: 99%

“…More details on this implementation are given [3] , at which an indicative workflow is proposed to be orchestrated as follows: Collect module, which is responsible for collecting data from social Web (Twitter and Blogosphere) and initializing new experiments when required by the researchers, submits new Parsing jobs (executed by Twitter or Blog Parsers) to the cloud via the Job Submission Client of Generic Worker, which is hosted at the Execution Service, when new data are available. The required data for each given job are uploaded as a batch, using the Data Access Service to Azure Blobs.…”

Section: The Cloud4trends Cloud-based Architecturementioning

confidence: 99%

See 4 more Smart Citations

Cloud-based architectures for geo-located blogosphere dynamics detection

2016

Self Cite

View full text Add to dashboard Cite

Social networking data threads emerge rapidly and such crowd-driven big data streams are valuable for detecting trends and opinions. For such analytics, conventional data mining approaches are challenged by both high-dimensionality and scalability concerns. Here, we leverage on the Cloud4Trends framework for collecting and analyzing geo-located microblogging content, partitioned into clusters under cloud-based infrastructures. Different cloud architectures are proposed to offer flexible solutions for geo-located data analytics with emphasis on incremental trend analysis. The proposed architectures are largely based on a set of service modules which facilitate the deployment of the experimentation on cloud infrastructures. Several experimentation remarks are highlighted to showcase the requirements and testing capabilities of different cloud computing settings. Keywords: social networks and wisdom of the crowd, geo-located blogosphere dynamics, social geo-located data clustering, cloud service deployment.

show abstract

Section: Micro-blogosphere Trends Detection: Status and Challengesmentioning

confidence: 99%

Section: Mining For Trend Analysismentioning

confidence: 99%

Section: Challenges In Crowdsourced Trend Analysismentioning

confidence: 99%

Section: Leveraging Cloud4trends For Social Text Dynamics Detectionmentioning

confidence: 99%

Section: The Cloud4trends Cloud-based Architecturementioning

confidence: 99%

See 3 more Smart Citations

Cloud-based architectures for geo-located blogosphere dynamics detection

2016

Self Cite

View full text Add to dashboard Cite

show abstract

Revisit Behavior in Social Media: The Phoenix-R Model and Discoveries

Figueiredo

Almeida

Matsubara

et al. 2014

Machine Learning and Knowledge Discovery in Databases

View full text Add to dashboard Cite

How many listens will an artist receive on a online radio? How about plays on a YouTube video? How many of these visits are new or returning users? Modeling and mining popularity dynamics of social activity has important implications for researchers, content creators and providers. We here investigate the effect of revisits (successive visits from a single user) on content popularity. Using four datasets of social activity, with up to tens of millions media objects (e.g., YouTube videos, Twitter hashtags or LastFM artists), we show the effect of revisits in the popularity evolution of such objects. Secondly, we propose the PHOENIX-R model which captures the popularity dynamics of individual objects. PHOENIX-R has the desired properties of being: (1) parsimonious, being based on the minimum description length principle, and achieving lower root mean squared error than state-of-the-art baselines; (2) applicable, the model is effective for predicting future popularity values of objects. 4

show abstract

KDE based outlier detection on distributed data streams in multimedia network

Zheng

Jeong

Huang

et al. 2016

Multimed Tools Appl

View full text Add to dashboard Cite

Multimedia networks hold the promise of facilitating large-scale, real-time data processing in complex environments. Their foreseeable applications will help protect and monitor military, environmental, safety-critical, or domestic infrastructures and resources. Cloud infrastructures promise to provide high performance and cost effective solutions to large scale data processing problems. This paper focused on the outlier detection over distributed data stream in real time, proposed kernel density estimation (KDE) based outlier detection algorithm KDEDisStrOut in Storm, firstly formalized the problem of outlier detection using the kernel density estimation technique and update the transported data incrementally between the child node and the coordinator node which reduces the communication cost. Then the paper adopted the exponential decay policy to keep pace with the transient and evolving natures of stream data and changed the weight of different data in the sliding window adaptively made the data analysis more reasonable. Theoretical analysis and experiments on Storm with synthetic and Multimed Tools Appl real data show that the KDEDisStrOut algorithm is efficient and effective compared with existing outlier detection algorithms, and more suitable for data streams.

show abstract

Social networking trends and dynamics detection via a cloud-based framework design

Cited by 22 publications

References 10 publications

Cloud-based architectures for geo-located blogosphere dynamics detection

Cloud-based architectures for geo-located blogosphere dynamics detection

Revisit Behavior in Social Media: The Phoenix-R Model and Discoveries

KDE based outlier detection on distributed data streams in multimedia network

Contact Info

Product

Resources

About