Page 92 - ISMCON souvenir 2021

ISMSCON - 2021

1. Both full texts and abstract articles were considered.
2. Articles including Books and Documents, Clinical trials, Meta-analysis and Systematic Reviews,
Randomized Control Trials and Review Articles were considered.
3. The language was limited to English
Upon searching the database with the above keywords, a total of 33 articles were identified out of which
18 articles were extracted by applying filters. The 18 articles were then assessed for eligibility and only 7
out of them were included. 1more article was included from related searches section and 2 articles were
included through Google Scholar, giving us a total of 10 studies.
RESULTS: The studies showed promising results in terms of immunogenicity produced in mice after oral
administration of the plant-derived vaccines. Specific immune responses were generated and both IgG
and IgA titers showed significant results. Studies also confirmed the adjuvant effect of the VP6 protein of
the rotavirus on immune response. Incorporation of fused Cholera Toxin B subunit with HRVVP-7 subunit
of the viral protein in Arabinopsis thaliana had also showed an adjuvant effect on the immune response
in one of the studies reviewed.
CONCLUSION: Although, human trials are yet to be conducted on the various plant-derived vaccines of
Rotavirus, there is significant evidence through animal studies to prove that if diligently administered to
human populations, the vaccine shall provide noteworthy results.

OS70: TWEET TOPICS ON CANCER AMONG INDIAN TWITTER

USERS – A MACHINE LEARNING ANALYSIS

Thilagavathi Ramamoorthy , Bagavandas Mappillairaju 2
1
Research Scholar, School of Public Health, SRM Institute of Science and Technology, Kattankulathur,
Chengalpattu District, Tamil Nadu, India-603 203, Email id: rmthilaga@gmail.com.
Professor, Centre for Statistics, SRM Institute of Science and Technology, Kattankulathur Chengalpattu District,
Tamil Nadu, India-603 203.

Background: Cancer is one of the leading cause of death among noncommunicable diseases in India.
Rapid dissemination of information in social media and its increased usage renders the possibility of
evaluating contents related to cancer prevention and management. The objective of this study was to
identify the topics of content shared regarding cancer in Twitter.

Methods: Twitter messages, geo coded within India, on cancer posted between September 15, 2021 to
October 15, 2021 had been retrieved using Twitter application programming interface based on keywords
identified from Sympular Signals. The tweets were pre-processed to remove the stop words, hashtags
and URLs. Data was visualized using word clouds and correlations between word tokens. Latent Dirichlet
allocation (LDA) topic model, an unsupervised machine learning technique was used to identify the
commonly discussed cancer topics. All analysis were carried out using R software version 4.1.1.
Results: A total of 13, 578 tweets were retrieved. After removing duplicates, 6487 tweets from 3189
unique twitter users revealed that majority of the tweets on cancer were on preventive measures and
treatment related information. The LDA analysis resulted in 5 topics: 1) Preventive measures 2) Symptom
awareness 3) Treatment modalities 4) Survivorship, seeking care and financial support 5) Dissemination
of research findings.
Conclusion: These findings indicate that Twitter is being used as a potential platform for better
communication and prompt dissemination of cancer related information to the public and policy makers
in India. In future, Social media might play a significant role in policy decisions and guide research
innovations related to cancer.

Keywords: Twitter, cancer, latent dirichlet allocation, machine learning, Topic modelling

90 CONFERENCE SOUVENIR