IRJEAS

INTERNATIONAL RESEARCH JOURNAL OF ENGINEERING & APPLIED SCIENCES

ISSN 2322-0821(E), ISSN 2394-9910(P)

An ISO 9001:2015 Certified Publication

Volume 12 Issue 2                        April-June 2024

Original Article

LICENCED UNDER

FIND ON

CROSSREF

SCILIT

 

CROSSMARK

Examining the Significance of Communication in the Context of Future Engineers: A Comparative Analysis

DOI: https://doi.org/10.55083/irjeas.2024.v12i02001

Country- IRAQ

  Intisar K. Saleh

PAPER ID: IRJEAS04V12I2001

Published: April 2024

Journal: IRJEAS, Volume 12, Issue 2

Pages: 01-07

Keywords: Interprofessional teamwork, communication skills, engineering education, comparative analysis and future engineers.

Abstract:

The study looks at how engineering teams may use communication to innovate, emphasising how important it is to communicate throughout the project’s ideation and implementation phases. It looks into how effective communication can encourage the exchange of ideas, spark creative thinking, and lead to the development of ground-breaking solutions for difficult technical challenges. The study also looks into how communication impacts project management practices, highlighting how crucial it is for setting clear objectives, monitoring due dates, and lowering risks. The research emphasises the critical relationship between communication skills and project performance in engineering pursuits by elucidating these connections. The ethical implications of communication in the engineering domain are also examined, with a focus on issues of honesty, integrity, and openness in interpersonal interactions. Through bringing these moral issues up in conversation, the study provides a thorough grasp of the function of communication in engineering practice and education. In order to cultivate a new generation of proficient communicators who will be able to foster innovation and growth in the sector, it also provides stakeholders in academia and industry with helpful ideas.

Cite this Article

Intisar K. Saleh Examining the Significance of Communication in the Context of Future Engineers: A Comparative Analysis. International Research Journal of Engineering & Applied Sciences (IRJEAS). 12(2), pp. 01-07, 2024. https://doi.org/10.55083/irjeas.2024.v12i02001.

Review Article

LICENCED UNDER

FIND ON

CROSSREF

SCILIT

 

CROSSMARK

The Potential and Limitations of Large Language Models for Text Classification through Synthetic Data Generation

DOI: https://doi.org/10.55083/irjeas.2024.v12i02002

Country- USA

Ashok Kumar Pamidi venkata, Leeladhar Gudala

PAPER ID: IRJEAS04V12I2002

Published: April 2024

Journal: IRJEAS, Volume 12, Issue 2

Pages: 08-15

Keywords: Large Language Models, Text Classification, Synthetic Data Generation, Natural Language Processing, Pretraining, Fine-tuning.

Abstract:

Large language models (LLMs), such as GPT-3 and BERT, have revolutionized the field of natural language processing (NLP), offering remarkable capabilities in text generation, translation, summarization, and classification. Among their many applications, LLMs show promise in text classification tasks, where they can automatically categorize text data into predefined categories or labels. This paper presents a comprehensive review of the potential and limitations of utilizing LLMs for text classification through synthetic data generation techniques. We delve into the methodologies employed in generating synthetic data using LLMs, which include techniques such as data augmentation, adversarial training, and transfer learning. These approaches aim to address issues of data scarcity and domain adaptation in text classification tasks. We explore their effectiveness in enhancing text classification performance, demonstrating how synthetic data can improve model generalization and robustness across diverse domains and languages. Additionally, we discuss the challenges and ethical considerations associated with synthetic data generation, including issues related to data privacy, bias amplification, and model fairness. Furthermore, we examine the impact of model size, pretraining data, and fine-tuning strategies on the performance of LLMs in text classification tasks. Recent studies have shown that larger models with access to more diverse pretraining data tend to achieve higher accuracy and better generalization on downstream tasks. Fine-tuning strategies, such as curriculum learning and self-training, can further improve model performance by adapting the model to task-specific data distributions. Through a critical analysis of existing literature and empirical studies, we provide insights into the current state-of-the-art techniques, identify key research gaps, and propose future directions for advancing the utilization of LLMs in text classification through synthetic data generation. This includes exploring novel approaches for generating diverse and representative synthetic data, developing evaluation metrics for assessing the quality of synthetic data, and investigating the long-term societal impacts of deploying LLMs in real-world applications.

Cite this Article

Ashok Kumar Pamidi venkata, Leeladhar Gudala. The Potential and Limitations of Large Language Models for Text Classification through Synthetic Data Generation: A Comparative Analysis. International Research Journal of Engineering & Applied Sciences (IRJEAS). 12(2), pp. 09-15, 2024.
https://doi.org/10.55083/irjeas.2024.v12i02002

Review Article

LICENCED UNDER

FIND ON

CROSSREF

SCILIT

 

CROSSMARK

Opinion Mining Using Hybrid Model Based on Deep Learning: Review

DOI: https://doi.org/10.55083/irjeas.2024.v12i02003

Country- INDIA

Jagriti Chand, Neha Lidoriya, Pooja Jayant

PAPER ID: IRJEAS04V12I2003

Published: April 2024

Journal: IRJEAS, Volume 12, Issue 2

Pages: 16-21

Keywords: Sentiment Analysis, Opinion Mining, Hybrid model, CNN, LSTM, Deep Learning.

Abstract:

In recent years, the proliferation of online platforms and social media has generated an unprecedented volume of user-generated content, including opinions and sentiments expressed across various domains. Opinion mining, also known as sentiment analysis, plays a crucial role in extracting valuable insights from this vast amount of data. This paper presents a novel approach to opinion mining utilizing a hybrid model based on deep learning techniques. The proposed model integrates the strengths of convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to effectively capture both local features and long-range dependencies in textual data. By leveraging this hybrid architecture, our model demonstrates enhanced performance in sentiment classification tasks compared to traditional methods. Experimental results on benchmark datasets showcase the effectiveness and robustness of the proposed approach in accurately analyzing and classifying opinions expressed in diverse contexts. Moreover, the model’s adaptability to different domains and its ability to handle noisy or ambiguous data further solidify its utility. This hybrid model not only advances the state-of-the-art in opinion mining but also holds promise for applications in market analysis, social media monitoring, and decision-making processes across various domains, providing valuable insights for businesses, policymakers, and researchers alike.

Cite this Article

Jagriti Chand et. al. Opinion Mining Using Hybrid Model Based on Deep Learning: Review: A Comparative Analysis. International Research Journal of Engineering & Applied Sciences (IRJEAS). 12(2), pp. 16-21, 2024.

https://doi.org/10.55083/irjeas.2024.v12i02003