Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Strength in Numbers: Using Big Data to Simplify Sentiment Classification.

Apostolos Filippas1, Theodoros Lappas2

  • 11 IOMS Department, NYU Stern School of Business , New York, New York.

Big Data
|September 22, 2017
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Thoracic epidural analgesia as part of an enhanced recovery program in gynecologic oncology: a prospective cohort study.

International journal of gynecological cancer : official journal of the International Gynecological Cancer Society·2023
Same author

Enhanced Recovery After Surgery Protocols in Obese Gynecological Oncology Patients: A Single-Center Experience.

Cureus·2023
Same author

Should patients with diabetes be encouraged to integrate social media into their care plan?

Future science OA·2018
Same author

Economic impact and policy implications from urban shared transportation: The case of Pittsburgh's shared bike system.

PloS one·2017
Same author

Levosimendan Improves Neurological Outcome in a Swine Model of Asphyxial Cardiac Arrest.

Heart, lung & circulation·2015
Same author

Axillary vessels and musculocutaneous nerve anatomic variation during ultrasound-guided regional anesthesia.

Regional anesthesia and pain medicine·2010
Same journal

Constructing an Artificial Intelligence-Driven Multilingual Medical Health Education Chatbot with Domain-Specific Medical Knowledge.

Big data·2026
Same journal

Explainable Machine Learning-Based Prediction of Postoperative Hypoxemia in Elderly Patients Undergoing General Anesthesia.

Big data·2026
Same journal

Big Data-Driven Video Anomaly Detection Using VideoMAE for Visual Analytics in CCTV Surveillance.

Big data·2026
Same journal

Agentic Artificial Intelligence-Driven Explainable Deep Learning for Deciphering Noncoding Pathogenic Mechanisms of Delirium Through Genomic Big Data Integration.

Big data·2026
Same journal

Personalized Driven Instruction Through Explainable Agentic AI in Multicultural Higher Education Environments.

Big data·2026
Same journal

Big Data-Driven Explainable Agentic AI Decision Frameworks for Enterprise Innovation in FinTech Ecosystems.

Big data·2026
See all related articles

BigCounter offers accurate and interpretable sentiment classification by leveraging Big Data instead of complex algorithms. This new method shows that beyond a certain point, more data yields diminishing returns for predictive performance.

Area of Science:

  • Natural Language Processing
  • Machine Learning
  • Computational Linguistics

Background:

  • Sentiment classification is crucial for applications like reputation monitoring and recommendation systems.
  • Current sentiment classification methods are increasingly complex and act as black-box predictors, hindering interpretability and tuning.
  • There is a need for accessible and justifiable sentiment classification tools for organizations with large unstructured datasets.

Purpose of the Study:

  • Introduce BigCounter, a novel algorithm for sentiment classification that prioritizes Big Data over algorithmic complexity.
  • To develop an accurate, interpretable, and parameter-free sentiment classification method.
  • To investigate the limits of Big Data in improving sentiment classification performance.

Main Methods:

Keywords:
big dataclassificationopinion miningsentiment analysis

Related Experiment Videos

  • Developed BigCounter, an algorithm combining standard data structures and statistical testing for sentiment classification.
  • Applied BigCounter to large datasets to study the impact of data volume on predictive accuracy.
  • Designed an efficient and parallelizable algorithm suitable for massive datasets.

Main Results:

  • BigCounter provides accurate and interpretable sentiment predictions.
  • The study found that predictive performance for sentiment classification converges after a certain data threshold.
  • Additional data beyond this point offers minimal improvement in predictive performance.

Conclusions:

  • BigCounter offers a practical, "out-of-the-box" solution for sentiment classification, reducing the need for specialized data science teams.
  • The findings suggest a "data-over-computation" paradigm for classification tasks, highlighting diminishing returns with excessive data.
  • The research lays the groundwork for future studies on optimizing data utilization in classification problems.