Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM62748
Volume:
10 |
5 |
May 2026
Pages:
1-7
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Computer Science and Engineering
MIT-ADT
Computer Science and Engineering
MIT-ADT
Computer Science and Engineering
MIT-ADT
Computer Science and Engineering
MIT-ADT
This paper presents a Multi-Platform Sentiment Analysis Dashboard - a web-based system, which integrates the sentiment analysis of four sources of data, text input by users, CSV/TXT files uploaded by users, YouTube comment threads, and BlueSky social media. This app relies on an NLP pipeline that sums the results of both VADER and TextBlob in order to classify any given input as a positive, negative, or neutral sentiment. Additionally, it has a specialised Finance Pulse feature, to correlate real-time stock price data obtained via the yfinance library with a finance news sentiment score, as provided by the Fin BERT model. The outcome of sentiment analysis is visualised as an interactive React.js UI component of donut charts, stacked bar charts, 7-day candlestick graphs, and rows can be exported as tables. The empirical tests were performed with the help of a 3,151 entries Amazon Alexa reviews dataset and a 100-sentence-long custom dataset. Application backend is based on Python based Fast API.
KEYWORDS
The most suitable solution would be the Multi-Platform Sentiment Analysis Dashboard, as it will allow combining sentiment analysis of data on different platforms such as Text, File, YouTube, Bluesky, and Financial news. This approach is effective due to the combination of VADER and TextBlob using an NLP engine to classify real-time data accurately and gain domain knowledge in the financial sector respectively. It has been run on five datasets. The backend, Fast API, and the frontend, React.js, can be expanded when necessary. The API backend written in fast API with React.js on the frontend can be expanded upon need. Each source is a distinct service and one can add more without altering the pipeline itself. This project is a good starting point in creating a complete-fledged sentiment intelligence solution that is multi-platform. It also demonstrates how to apply a natural language processing to over one third-party API in the natural world, which adds value.
[1] B. Pang and L. Lee, "Opinion Mining and Sentiment Analysis," Foundations and Trends in Information Retrieval, vol. 2, no. 1–2, pp. 1–135, 2008. [2] C. J. Hutto and E. Gilbert, "VADER: A Parsimonious Rule-based Model for Sentiment Analysis of Social Media Text," in Proc. 8th Int. Conf. Weblogs Social Media (ICWSM), Ann Arbour, Michigan, 2014. [3] S. Loria, "TextBlob: Simplified Text Processing," 2018. [Online]. Available: https://textblob.readthedocs.io [4] Y. Liu, Z. Mao, R. Geng, J. Chen, and H. Ye, "FinBERT: A Pre-trained Financial Language Representation Model for Financial Text Mining," in Proc. IJCAI 2020, pp. 4513–4519. [5] J. Bollen, H. Mao, and X. Zeng, "Twitter mood predicts the stock market," Journal of Computational Science, vol. 2, no. 1, pp. 1–8, 2011. [6] S. Ramírez, "FastAPI: Modern, Fast Web Framework for Building APIs with Python 3.6+," 2018. [Online]. Available: https://fastapi.tiangolo.com [7] Google LLC, "YouTube Data API v3 Reference," 2024. [Online]. Available: https://developers.google.com/youtube/v3 [8] AT Protocol Authors, "AT Protocol Specification — Bluesky Social," 2023. [Online]. Available: https://atproto.com/docs [9] Finnhub.io, "Finnhub Stock API — Real-Time Stock Data and Financial News," 2024. [Online]. Available: https://finnhub.io/docs/api [10] Recharts Team, "Recharts — A Composable Charting Library Built on React Components," 2021. [Online]. Available: https://recharts.org
Publication Date
5/8/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
4
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...