Sentiment-Aware Stock Recommendation Using a Hybrid NLP and Machine Learning Approach
Dandao Xuebao/Journal of Ballistics · 17.06.2026 · 38 (2) · 646-655
DOI: 10.52783/dxjb.v38.400 ↗Kurz gefasst
Fachartikel in der Zeitschrift Dandao Xuebao/Journal of Ballistics, online erschienen am 17.06.2026. Verfasst von V.Manju Satya Sai Durga und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Stock Price and Sentiment Analysis Management System (SPCM) is an advanced web-based financial analytical system, which seeks to streamline the process of making investment decisions by integrating the application of Machine Learning (ML), Natural language Processing (NLP) and real-time data analytics. The traditional method of the conventional stock market prediction model is based on the use of historical numerical data that often fails to represent the mood of the market as observed in the news articles, social media and popular opinion. In order to overcome these weaknesses, the proposed system will integrate structured data (stock price, volume and the stock trends) with the unstructured data (financial news and financial information provided on social media) so as to offer a comprehensive view of the market processes. The system is implemented using Django framework and consists of various intelligent modules including real-time stock tracking, sentiment analysis, predictive modeling, a hybrid recommendation engine, etc. NLP methods, such as TF-IDF vectorization, VADER sentiment analysis and Word2Vec embeddings, are performed to do the textual data, which will be classified as positive, negative, or neutral sentiment. This sentiment information is used in conjunction with machine learning models like Linear Regression, Decision Tree, Random Forest and XGBoost to predict the changes in the stock price and volatility. In addition, the system applies a hybrid recommendation system which consists of content based filtering and collaborative filtering to deliver personalized investment recommendation, based on the user behavior, sentiment trends and the market performance indicators. The platform also provides user authentication, portfolio management and interactive data visualization dashboards. Analysis of the outcomes from the experiments demonstrates that sentiment analysis together with conventional financial data gets the accuracy of prediction and interaction with the user significantly increased. The system provides the investors with the information that can be acted upon, to make informed and strategic decisions. Altogether, SPCM indicates that NLP and ML can be effectively implemented in a scalable web-based structure to develop an intelligent and data-driven stock analysis and recommendation platform that can be used in financial settings of the current time.
Zitieren
APA
Durga, V. S. S., & Rajeswari, K. (2026). Sentiment-Aware Stock Recommendation Using a Hybrid NLP and Machine Learning Approach. Dandao Xuebao/Journal of Ballistics, 38(2), 646-655. https://doi.org/10.52783/dxjb.v38.400
Vancouver
Durga VSS, Rajeswari K. Sentiment-Aware Stock Recommendation Using a Hybrid NLP and Machine Learning Approach. Dandao Xuebao/Journal of Ballistics. 2026;38(2):646-655. doi:10.52783/dxjb.v38.400
BibTeX
@article{Durga2026,
author = {Durga, V.Manju Satya Sai and Rajeswari, K.Naga},
title = {Sentiment-Aware Stock Recommendation Using a Hybrid NLP and Machine Learning Approach},
journal = {Dandao Xuebao/Journal of Ballistics},
year = {2026},
volume = {38},
number = {2},
pages = {646--655},
doi = {10.52783/dxjb.v38.400}
}
EUVIMED