Conical Classification For Computationally Efficient One-Class Topic Determination
–arXiv.org Artificial Intelligence
As the Internet grows in size, so does the amount of text based information that exists. For many application spaces it is paramount to isolate and identify texts that relate to a particular topic. While one-class classification would be ideal for such analysis, there is a relative lack of research regarding efficient approaches with high predictive power. By noting that the range of documents we wish to identify can be represented as positive linear combinations of the Vector Space Model representing our text, we propose Conical classification, an approach that allows us to identify if a document is of a particular topic in a computationally efficient manner. We also propose Normal Exclusion, a modified version of Bi-Normal Separation that makes it more suitable within the one-class classification context. We show in our analysis that our approach not only has higher predictive power on our datasets, but is also faster to compute.
arXiv.org Artificial Intelligence
Oct-30-2021
- Country:
- Africa > South Africa (0.04)
- Oceania
- New Zealand (0.04)
- Australia (0.04)
- North America
- Canada (0.04)
- United States > California
- Santa Clara County > Palo Alto (0.04)
- Europe
- United Kingdom (0.04)
- Ireland (0.04)
- Asia
- Genre:
- Research Report (0.82)
- Industry:
- Information Technology > Security & Privacy (1.00)
- Health & Medicine > Therapeutic Area (0.69)
- Technology:
- Information Technology
- Security & Privacy (1.00)
- Data Science (1.00)
- Communications > Social Media (0.93)
- Artificial Intelligence
- Natural Language
- Text Classification (0.95)
- Text Processing (0.68)
- Machine Learning
- Neural Networks > Deep Learning (1.00)
- Statistical Learning (0.68)
- Performance Analysis > Accuracy (0.68)
- Supervised Learning (0.66)
- Natural Language
- Information Technology