Simulations and Security Processes

Talabis, Mark; McPherson, R. A.; Miyamoto, Inez; Martin, Jeffrey W.; Kaye, Dalia Dassa

doi:10.1016/b978-0-12-800207-0.00004-6

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This learning paradigm is a powerful tool for data classification using machine language. However, supervised learning requires the availability of accurately labeled datasets to infer learning models [4]. Despite the learning capability of the state-of-the-art supervised machine learning algorithms, the continuously growing size of the datasets used to train the models has made the labeling an even more costly process in terms of time and effort.…”

Section: Introductionmentioning

confidence: 99%

Soft Semi-Supervised Deep Learning-Based Clustering

AlZuhair,

Ben Ismail,

Bchir

2023

Applied Sciences

View full text Add to dashboard Cite

Semi-supervised clustering typically relies on both labeled and unlabeled data to guide the learning process towards the optimal data partition and to prevent falling into local minima. However, researchers’ efforts made to improve existing semi-supervised clustering approaches are relatively scarce compared to the contributions made to enhance the state-of-the-art fully unsupervised clustering approaches. In this paper, we propose a novel semi-supervised deep clustering approach, named Soft Constrained Deep Clustering (SC-DEC), that aims to address the limitations exhibited by existing semi-supervised clustering approaches. Specifically, the proposed approach leverages a deep neural network architecture and generates fuzzy membership degrees that better reflect the true partition of the data. In particular, the proposed approach uses side-information and formulates it as a set of soft pairwise constraints to supervise the machine learning process. This supervision information is expressed using rather relaxed constraints named “should-link” constraints. Such constraints determine whether the pairs of data instances should be assigned to the same or different cluster(s). In fact, the clustering task was formulated as an optimization problem via the minimization of a novel objective function. Moreover, the proposed approach’s performance was assessed via extensive experiments using benchmark datasets. Furthermore, the proposed approach was compared to relevant state-of-the-art clustering algorithms, and the obtained results demonstrate the impact of using minimal previous knowledge about the data in improving the overall clustering performance.

show abstract

Section: Introductionmentioning

confidence: 99%

Soft Semi-Supervised Deep Learning-Based Clustering

AlZuhair,

Ben Ismail,

Bchir

2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…These techniques facilitate a thorough examination of content that resonates with users interested in virtual marketing. The use of big data analytics helps in identifying patterns in the behavior of social media users engaging with virtual marketing content (Talabis et al, 2014). This includes both a broad analysis (covering aspects like posts, comments, and shares linked to virtual marketing) and a more granular examination, shedding light on individual user behaviors over time.…”

mentioning

confidence: 99%

VirtualMarketing Dynamics: Leximancer-Driven Insights from Social Media Trends

Balcıoğlu

2024

isarder

View full text Add to dashboard Cite

Purpose –This study explores into the field of virtual marketing, an essential aspect of contemporary business strategies that utilizes web-based technologies for the efficient dissemination and engagement of marketing content. It aims to decipher how virtual marketing is portrayed and discussed in user-generated content (UGC) on social media platforms, with a specific focus on Instagram.Design/methodology/approach-The research employs a mix of text mining, thematic analysis, and textual analysis to scrutinize a substantial dataset of social media posts related to #VirtualMarketing. It integrates Social Exchange Theory and the Social Media User Engagement Framework to investigate user engagement dynamics on social media platforms. This methodology enables a comprehensive examination of themes, and engagement patterns in UGC that is related to virtual marketing. Advanced data analysis tools, including Leximancer for thematic content analysis and Python is applied.Findings –The findings reveal that virtual marketing on social media covers a broad range of practices, from entirely digitalized strategies to hybrid models that incorporate traditional marketing elements. The study identifies the predominant themes in virtual marketing, assesses the textual orientation of the related content, and explores the relationship between these themes and various user engagement metrics.Discussion –These findings underscore the pivotal role of social media in shaping virtual marketing strategies and emphasize the necessity for more extensive content analysis in this area. The study contributes to the academic discourse on virtual marketing by providing empirical insights into the trends and patterns present within UGC. Furthermore, it presents a practical framework for the analysis of large-scale textual data on social media, showcasing the effectiveness of computational qualitative analysis with NLP in enhancing understanding and strategies in virtual marketing. This research provides a valuable resource for future studies in the social sciences, especially those utilizing NLP to investigate the dynamics of virtual marketing.

show abstract

Simulations and Security Processes

Cited by 2 publications

References 0 publications

Soft Semi-Supervised Deep Learning-Based Clustering

Soft Semi-Supervised Deep Learning-Based Clustering

VirtualMarketing Dynamics: Leximancer-Driven Insights from Social Media Trends

Contact Info

Product

Resources

About