Amazon Technologies, Inc.

Joshua Seth Levy

Dilek Zeynep Hakkani-Tur

Yang Liu

Saurabh Gupta

Anna Chen Santos

Thomas Irvine Nelson

Yelin Kim

Brian Lafayette Adair

Described herein is a system for improving sentiment detection and/or recognition using multiple inputs. For example, an autonomously motile device is configured to generate audio data and/or image data and perform sentiment detection processing. The device may process the audio data and the image data using a multimodal temporal attention model to generate sentiment data that estimates a sentiment score and/or a sentiment category. In some examples, the device may also process language data (e.g., lexical information) using the multimodal temporal attention model. The device can adjust its operations based on the sentiment data. For example, the device may improve an interaction with the user by estimating the user's current emotional state, or can change a position of the device and/or sensor(s) of the device relative to the user to improve an accuracy of the sentiment data.

Multimodal sentiment detection

Features are disclosed for identifying indirect user feedback and providing content such as item descriptions based on the indirect user feedback. An indirect feedback system may receive sensed data such as images or audio and identify indicators of indirect feedback for the subject shown, heard, or otherwise detected in the sensed data. For example, a user's facial expression and/or body language can provide indirect feedback as to how the user is feeling (e.g., mood). Based on the detected mood, features for suggesting additional items that should appeal to the user are described.

Indirect feedback systems and methods

Growing community of inventors

San Francisco, CA, United States of America

Joshua Seth Levy