Impact of Stemming on Efficiency of Messages Likelihood Definition in Telegram Newsfeeds

Barkovska, Olesia; Rusnak, Patrik; Tkachov, Vitalii; Muzyka, Tetiana

doi:10.1109/khpiweek57572.2022.9916415

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The text of social media posts is shortened instead of being in complete sentences, and so if less text is present in the data, the performance of models with a high dependence on the text may degrade [47]. Smaller text is often used when blogging on a particular topic, ignoring auxiliary elements such as suffixes and endings, and shortening the word to its stem [48]. To resolve the mentioned issues, we proposed a multilayered preprocessing approach consisting of four layers that could be used sequentially, one-by-one, or independently: Layer 1.…”

Section: Multilayered Preprocessing Approach For Social Media Message...mentioning

confidence: 99%

A Multilayered Preprocessing Approach for Recognition and Classification of Malicious Social Network Messages

Čepulionytė,

Toldinas,

Lozinskis

2023

Electronics

View full text Add to dashboard Cite

The primary methods of communication in the modern world are social networks, which are rife with harmful messages that can injure both psychologically and financially. Most websites do not offer services that automatically delete or send malicious communications back to the sender for correction, or notify the sender of inaccuracies in the content of the messages. The deployment of such systems could make use of techniques for identifying and categorizing harmful messages. This paper suggests a novel multilayered preprocessing approach for the recognition and classification of malicious social network messages to limit negative impact, resulting in fewer toxic messages, scams, and aggressive comments in social media messages and commenting areas. As a result, less technical knowledge would be required to investigate the effects of harmful messages. The dataset was created using the regional Lithuanian language with four classes: aggressive, insulting, toxic, and malicious. Three machine learning algorithms were examined, five use cases of a multilayered preprocessing approach were suggested, and experiments were conducted to identify and classify harmful messages in the Lithuanian language.

show abstract

Section: Multilayered Preprocessing Approach For Social Media Message...mentioning

confidence: 99%

A Multilayered Preprocessing Approach for Recognition and Classification of Malicious Social Network Messages

Čepulionytė,

Toldinas,

Lozinskis

2023

Electronics

View full text Add to dashboard Cite

show abstract

“…Current research explores methods of visualizing the skeletal animation process, based on the use of control points to manage limb movements [3]. It examines the importance of this topic and its impact on creating realistic and effective visual projects in the modern world of digital graphics [4][5][6] and reproduction.…”

Section: Introductionmentioning

confidence: 99%

Improved Rendering Method of Skeletal Animation on Control Points Base

BARKOVSKA,

BILICHENKO,

UVAROV

et al. 2024

CSIT

View full text Add to dashboard Cite

Current research builds on an investigation of skeletal animation methods, focusing on the use of control points for managing limb movements. It thoroughly considers the relevance and significance of the chosen topic and its impact on creating realistic and effective visual projects in the modern world of digital graphics and reproduction. The research includes an analysis of the impact of sample quantity on the frame transitions smoothness and the rendering time to achieve a balance between quality and efficiency. It also involves refining the method through adaptation for execution on a GPU graphic processor. Studied Blender 3D engines (EEEVE and Cycles) allowed to analyze rendering performance on different computational architectures – CPU and GPU depending on sample values (60 and 128), frame number (250, 500, and 1000), and also the frame frequency at a rate of 30 frames per second. The goal of the research was an achievement of optimal balance between performance and realism in animation details reproduction. Three experiments were done to reach this goal and make the following conclusion: graphical processor utilization through the Cycles engine demonstrated a rendering acceleration of 43%, ranging from minimal to maximum settings. In the same time, the acceleration of the hybrid system via the EEVEE engine showed an acceleration of 15.2% only.

show abstract

Impact of Stemming on Efficiency of Messages Likelihood Definition in Telegram Newsfeeds

Cited by 2 publications

References 0 publications

A Multilayered Preprocessing Approach for Recognition and Classification of Malicious Social Network Messages

A Multilayered Preprocessing Approach for Recognition and Classification of Malicious Social Network Messages

Improved Rendering Method of Skeletal Animation on Control Points Base

Contact Info

Product

Resources

About