Online reviews can suffer from certain reliability problems due to reasons such as reviewer bias, lack of reviewer objectivity, insufficient number of reviews, etc. This disclosure describes techniques for generating reviews using evidence gathered from hard data sources rather than from subjective user opinion. Example data sources that can be used to generate evidence-based reviews include IoT sensors internal to the reviewed entity; publicly available information external to the reviewed entity; and data from related reviews applicable to the currently reviewed entity. The evidence-based reviews described herein enable a reader to look beneath the reviews to see the data that led to the review score. The described techniques reduce or eliminate bias in reviews and increase reader confidence in them.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.