	US 12,260,661 B2
	Topic classifier with sentiment analysis
Takuya Goto, Kodaira (JP); and Yoshiroh Kamiyama, Setagaya-ku (JP)
Assigned to International Business Machines Corporation, Armonk, NY (US)
Filed by International Business Machines Corporation, Armonk, NY (US)
Filed on Mar. 25, 2022, as Appl. No. 17/656,467.
Prior Publication US 2023/0306770 A1, Sep. 28, 2023
Int. Cl. G06K 9/00 (2022.01); G06N 20/00 (2019.01); G06V 30/19 (2022.01); G06V 30/41 (2022.01)

CPC G06V 30/41 (2022.01) [G06N 20/00 (2019.01); G06V 30/1912 (2022.01); G06V 30/1916 (2022.01)]

20 Claims

1. A method, comprising:

receiving a set of documents;

selecting a topic;

determining that a first document from the set contains a topic label for the topic;

generating a topic sentiment score for the first document;

adding the topic sentiment score to a set of training data;

determining that a second document from the set does not contain the topic label;

generating an average sentiment score for the second document; and

generating a bias factor for the average sentiment score.