Survey on Social Networks Data Analysis

Jaffali, Soufiene; Jamoussi, Salma; Khelifi, Nesrine; Hamadou, Abdelmajid Ben

doi:10.1007/978-3-030-37484-6_6

Cited by 9 publications

(8 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Song et al ( 2014 ) presented a survey about short-text characteristics, challenges, and classification that were divided into four basic types, namely, the usage of semantic analysis, classification using semi-supervised methods, fusion-based ensemble technique, and real-time classification. Jaffali et al ( 2020 ) presented a summary of social network data analysis, including its essential methods and applications in the context of structural social media data analysis. They structured the social network analysis methods into two types, namely, structural analysis methods (which study the structure of the social network like friendships), and added-content methods (which study the content added by users).…”

Section: Literature Reviewmentioning

confidence: 99%

Using Topic Modeling Methods for Short-Text Data: A Comparative Analysis

Albalawi

Yeap

Benyoucef

2020

Front. Artif. Intell.

246

130

View full text Add to dashboard Cite

With the growth of online social network platforms and applications, large amounts of textual user-generated content are created daily in the form of comments, reviews, and short-text messages. As a result, users often find it challenging to discover useful information or more on the topic being discussed from such content. Machine learning and natural language processing algorithms are used to analyze the massive amount of textual social media data available online, including topic modeling techniques that have gained popularity in recent years. This paper investigates the topic modeling subject and its common application areas, methods, and tools. Also, we examine and compare five frequently used topic modeling methods, as applied to short textual social data, to show their benefits practically in detecting important topics. These methods are latent semantic analysis, latent Dirichlet allocation, non-negative matrix factorization, random projection, and principal component analysis. Two textual datasets were selected to evaluate the performance of included topic modeling methods based on the topic quality and some standard statistical evaluation metrics, like recall, precision, F -score, and topic coherence. As a result, latent Dirichlet allocation and non-negative matrix factorization methods delivered more meaningful extracted topics and obtained good results. The paper sheds light on some common topic modeling methods in a short-text context and provides direction for researchers who seek to apply these methods.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Using Topic Modeling Methods for Short-Text Data: A Comparative Analysis

Albalawi

Yeap

Benyoucef

2020

Front. Artif. Intell.

246

130

View full text Add to dashboard Cite

show abstract

“…Today the study of the tags is intensely conducted for marketing purposes (for example, [39]), but more complex technologies are actively developing in social networks such as text analysis, which allow clustering (hierarchical, partitional, semantic) and classification predicated on ontology-based and machine learning-based methods [40], as well as the determination the semantic type of tags [41]. The analysis of the emotional color of E3S Web of Conferences 164, 12007 (2020) TPACEE-2019 https://doi.org/10.1051/e3sconf /202016412007 messages and visual content is a more complex task that will take the ability to analyze social trends to a new level.…”

Section: Methodsmentioning

confidence: 99%

Potential of students’ project work using the example of childfree phenomenon analysis

Nam

2020

E3S Web Conf.

View full text Add to dashboard Cite

Information and communication technologies create new educational opportunities, and the most obvious of which are related to e-learning. Nowadays Internet provides great opportunities for organizing a team project work. The article considers an example of quantitative and content analysis of authentic materials and relevant themes in social networks while studying English. The phenomenon of “childfree” is rather common trend among young people, analysis of which could serve as an incentive to motivate them in acquiring real practical knowledge and skills. The study revealed that statements on this topic are overwhelmingly made by women who can praise a childless lifestyle; that there are different problems related to having children and fears related to pregnancy, childbirth, etc. Photos (selfies, happy moments with pets, frames from travel, achievements in sport) in social networks exacerbate the situation by providing an attractive alternative to families with children, and extra evidence to verbalized rational reasons for supporting “childfree”. The studied example shows that such kind of project work fosters developing critical thinking, language, intercultural, and analytical skills.

show abstract

“…Another area where ML algorithms are effective is in the discovery, in a bottom-up or data-driven fashion, of novel relationships in multidimensional data (Bishop 2006). This approach has demonstrated effectiveness in multiple fields (Bishop 2006, LeCun et al, 2015) ranging across financial services (e.g., stock market analysis (Lopez de Prado, 2018), fraud detection (Chalapathy et al, 2019)), clinical applications (e.g., disease diagnosis (Heinrichs et al, 2019) and progression prediction (Wang, 2019)), drug discovery (Ekins et al, 2019), robotics (Wang et al, 2019, Oshin et al, 2019), and social media (e.g., social network data analysis (Jaffali et al, 2019) and content filtering (Dada et al, 2019)). Within the broader healthcare field, one area where ML may be useful is in the discovery of biomarkers (e.g., predictors of illness development or course, see Leclerq et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

Using Machine Learning to Classify Schizophrenia Based on Retinal Images

Joseph

Lai

Silverstein

et al. 2021

Preprint

View full text Add to dashboard Cite

Objectives: Thinning of retinal layers has been documented in patients with chronic schizophrenia using standard metrics of optical coherence tomography (OCT) devices. We demonstrate the effectiveness of machine learning (ML) techniques to differentiate between schizophrenia patients and healthy controls using OCT images. Methods: Features extracted from a convolutional neural network (CNN) designed to segment retinal layers from OCT images represented abstracted data from the OCT images of 14 first episode (FEP) and 18 chronic schizophrenia patients, and their respective 20 and 18 age-matched controls. The abstracted data and OCT machine metrics were used separately to train support vector classification (SVC) models to differentiate between control and schizophrenia samples and test them. Results: SVCs operating on OCT machine metrics did not classify unseen samples of FEP schizophrenia patients and controls with performance better than chance, while those looking at chronic schizophrenia did, paralleling results obtained using parametric statistics. In contrast, SVCs operating on OCT image data extracted from the CNN classified unseen samples from both populations with performance greater than chance. Conclusion: These results suggest that ML techniques can detect patterns in patients with FEP schizophrenia with greater performance using features extracted from OCT images than metrics provided by OCT machines.

show abstract

Survey on Social Networks Data Analysis

Cited by 9 publications

References 77 publications

Using Topic Modeling Methods for Short-Text Data: A Comparative Analysis

Using Topic Modeling Methods for Short-Text Data: A Comparative Analysis

Potential of students’ project work using the example of childfree phenomenon analysis

Using Machine Learning to Classify Schizophrenia Based on Retinal Images

Contact Info

Product

Resources

About