Scenario-feature identification from online reviews based on BERT.

Scenario endows a product with meanings. It has become the key to win the competition to design a product according to specific usage scene. Traditional scenario identification and product feature association methods have disadvantages such as subjectivity, high cost, coarse granularity, and limited scenario can be identified. In this regard, we propose a BERT-based scenario-feature identification model to effectively extract the information about users' experience and usage scene from online reviews. First, the scenario-feature identification framework is proposed to depict the whole identification process. Then, the BERT-based scene-sentence recognition model is constructed. The Skip-gram and word vector similarity methods are used to construct the scene and feature lexicon. Finally, the triad is constructed through the analysis of scene-feature co-occurrence matrix, which realizes the association of scenario and product features. This proposed model is of great practical value for product developers to better understand customer's requirements in specific scenarios. The experiments of scenario-feature identification from the reviews of Pacific Auto verifies the effectiveness of this method.

Predicting the water film depth: A model based on the geometric features of road and capacity of drainage facilities.

The water film depth is a key variable that affects traffic safety under rainfall conditions. According to the Federal Highway Administration, approximately 5700 people are killed and more than 544 700 people are injured in crashes on wet pavements annually. While several studies have attempted to address water film depth issues by establishing prediction models, a few focused on the relationship among road geometric features, capacity of drainage facilities and water film depth. To ascertain the influence of the geometric features of road and facility drainage capacities on the water film depth, the road geometry features were first classified into four types, and the facility drainage capacities were considered from three aspects in this study. Furthermore, the concept of short-time rainfall grade was proposed according to the results of the field test. Finally, the theoretical prediction model for the water film depth was conceived, based on the geometric features of road and facility drainage capacities with different rainfall intensities. Compared with the traditional regression prediction models, the theoretical prediction model clearly shows the effects of the geometric features of road and facility drainage capacities. When the road drainage facilities have no drainage capacity, the water film depth increases rapidly with the rainfall intensity. This model can be used to predict the water film depth of road surfaces on rainy days, evaluate the effect of rainfall on the driving environment, and provide guidance for determining safety control measures on rainy days.