Rachna Narula

Ms. Rachna Narula

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 May 2025 in International Journal of Information Technology
Verified
Journal Article
Closed access
PDF file
MKMahesh Kumar
Mahesh Kumar
SSSHALU Shalu
SHALU Shalu
ADAjay Dureja
Ajay Dureja
RNRachna Narula
Rachna Narula
Shyla ShylaShyla Shyla
Shyla Shyla
RARavi Arora
Ravi Arora

3 August 2023
Verified
Conference Paper
Open access
ANAastha Nautiyal
Aastha Nautiyal
DBDevesh Kumar Bhardwaj
Devesh Kumar Bhardwaj
RNRachna Narula
Rachna Narula
HSHarshendra Singh
Harshendra Singh
Human emotions can be recognized and studied in great detail in the field of computer vision, on which various types of research have already been conducted. Python, the Open-Source Computer Vision Library (OpenCV), and NumPy were used to implement the work. To predict emotion, the training dataset is compared to the scanned image (testing dataset). The goal of this research is to create a system that can analyze a photograph and forecast the facial expression of a subject. The study shows that this process is practical and yields reliable outcomes. Face recognition has existed for a long time. Moving forward, human emotion that is expressed on the face and experienced by the brain can be roughly captured in video or image form. Human emotion recognition is urgently needed so that cutting-edge, artificially intelligent systems can mimic and interpret facial expressions. This can be useful in helping to identify threats to security or to intent while making judgments. In this work, we want to address the crowd security threat that may affect a broader population by averting violent scenarios (such as mob lynchings, protests, and teenage wrath), identifying such possible threats, and warning people in advance. We employ a method called facial recognition crowd sentiment detection. Additionally, it can be used to spot upsetting events like car accidents.

30 September 2024
Verified
Book Chapter
Closed access
PDF file
HDHimani Dhawan
Himani Dhawan
SRShayoni Rakshit
Shayoni Rakshit
TGTanya Gupta
Tanya Gupta
RNRachna Narula
Rachna Narula
VKVIJAY KUMAR
VIJAY KUMAR

2 July 2026
Verified
Book Chapter
Closed access
PDF file
VKVIJAY KUMAR
VIJAY KUMAR
SVSrishti Vashishtha
Srishti Vashishtha
PMPayal Malik
Payal Malik
RNRachna Narula
Rachna Narula
GEGeeta
Geeta

1 April 2026
Verified
Book Chapter
Closed access
PDF file
RNRachna Narula
Rachna Narula
UHUdit Hasija
Udit Hasija
VKVIJAY KUMAR
VIJAY KUMAR
NRNitasha Rathore
Nitasha Rathore

30 July 2026 in Journal of Communication, Language and Culture
Verified
Journal Article
Open access
PDF file
RNRachna Narula
Rachna Narula
VGVedika Gupta
Vedika Gupta
JKJawad Khan
Jawad Khan
TRTariq Rahim
Tariq Rahim
VKVIJAY KUMAR
VIJAY KUMAR
Hate speech on digital communication platforms has become a major obstacle to healthy online discourse, especially in multilingual societies such as India, where Hindi is a dominant language in social media interactions. Hostile, offensive, and defamatory speech is linguistically and socio-culturally complex because of colloquial idioms, regional variations, code-mixing, and culturally embedded references. However, effective detection is crucial for creating safer and more inclusive digital communication environments. This study evaluates advanced language models for analysing hate speech in Hindi social media content. A dataset of 21000 Hindi posts from Twitter and public repositories, categorized into five categories, was analysed: hate, offensive, fake, defamation, and non-hostile. General-purpose models were tested against Hindi-specific language models, including Hindi-BERT (based on Bidirectional Encoder Representations from Transformers, or BERT) and MuRIL, to investigate whether performance can be further enhanced by integrating Long Short-Term Memory (LSTM) layers. In tests, the best-performing model, Hindi-BERT (with sequential learning added), correctly identified 94 out of every 100 posts—a considerable improvement over simpler models. For social media platforms, it has real-world consequences: it can automatically identify harmful content to be reviewed by a human, minimize nuisance alerts that waste human moderators' time, and identify defamatory or bogus posts before they gain a lot of traction. The results offer a systematic approach to researching how hostility develops in the Hindi-speaking online community, how linguistic creativity (e.g., slang, sarcasm, code-mixing) can conceal or manifest hostility, and how decisions about content moderation influence public discourse for communication scholars. Overall, this paper illustrates that language-specific computational tools can be used for both platform governance and communication research, provided that the cultural context is considered. Finally, technical methods are combined with communication scholarship to explain and curb harmful speech in the online public sphere.