The Size of Contact-Implicit Preference Relationships: Two Large Sample Tests

This work examines relationships between friendships and implicit preferences across two large samples. There is considerable evidence in the contact literature suggesting that friendships relate to more favorable attitudes toward outgroups, however, most evidence reflects explicit self-report measures. Using samples of 235,543 participants who completed the Disability IAT and 533,220 participants who completed the Sexuality IAT on the Project Implicit website, results indicate that participants reporting either a disabled friend or close acquaintance demonstrated weaker implicit preferences for abled over disabled people. Similarly, those with gay friends demonstrated weaker implicit preference for “straight” over gay. The size of these relationships were considerably smaller than found for explicit evaluations.

Personalized Recommendation Model: An Online Comment Sentiment Based Analysis

Traditional recommendation algorithms measure users’ online ratings of goods and services but ignore the information contained in written reviews, resulting in lowered personalized recommendation accuracy. Users’ reviews express opinions and reflect implicit preferences and emotions towards the features of products or services. This paper proposes a model for the fine-grained analysis of emotions expressed in users’ online written reviews, using film reviews on the Chinese social networking site Douban.com as an example. The model extracts feature-sentiment word pairs in user reviews according to four syntactic dependencies, examines film features, and scores the sentiment values of film features according to user preferences. User group personalized recommendations are realized through user clustering and user similarity calculation. Experiments show that the extraction of user feature-sentiment word pairs based on four syntactic dependencies can better identify the implicit preferences of users, apply them to recommendations and thereby increase recommendation accuracy.