Improving Gender Prediction of Social Media Users via Weighted Annotator Rationales
نویسنده
چکیده
This paper proposes and contrastively evaluates several novel approaches to utilizing annotator rationales to improve the prediction of user gender in social media for English and Spanish. Our methods outperform state-of-the-art systems for Twitter gender prediction, and yield up to 28% error reduction relative to an otherwise identical system and training data without the use of annotator rationales.
منابع مشابه
The Relationship between virtual social networks usage and gender role attitude in university students of Iran
Background & aim: Gender role attitude is one of the key issues affecting the stability of family foundation, which is under the influence of mass media. New media and the process of globalization are effective in promoting gender equality, and an example of modern media is virtual social networks. This study aimed to determine the relationship between virtual social media usage and gender role...
متن کاملAuthor gender identification from text using Bayesian Random Forest
Nowadays high usage of users from virtual environments and their connection via social networks like Facebook, Instagram, and Twitter shows the necessity of finding out shared subjects in this environment more than before. There are several applications that benefit from reliable methods for inferring age and gender of users in social media. Such applications exist across a wide area of fields,...
متن کاملCorpus for Customer Purchase Behavior Prediction in Social Media
Many people post about their daily life on social media. These posts may include information about the purchase activity of people, and insights useful to companies can be derived from them: e.g. profile information of a user who mentioned something about their product. As a further advanced analysis, we consider extracting users who are likely to buy a product from the set of users who mention...
متن کاملFactors Affecting Social Commerce and Exploring the Mediating Role of Perceived Risk (Case Study: Social Media Users in Isfahan)
Owing to the ever-increasing prevalence of social media use, social commerce has become an important part of e-commerce. This study endeavors to explore the impact of social media quality and social support on the social commerce (SC) intention directly and through the variable of perceived risk. The sample included 214 social media users in Isfahan collected through simple random sampling meth...
متن کاملPrediction of user's trustworthiness in web-based social networks via text mining
In Social networks, users need a proper estimation of trust in others to be able to initialize reliable relationships. Some trust evaluation mechanisms have been offered, which use direct ratings to calculate or propagate trust values. However, in some web-based social networks where users only have binary relationships, there is no direct rating available. Therefore, a new method is required t...
متن کامل