Abstract
Demographic attribute inference of social networking service (SNS) users is a valuable application for marketing and for targeting advertisements. Several studies have examined Twitter-user gender inference in natural language processing, image recognition, and other research domains. Reportedly, a combined approach using text data and image data outperforms an individual data approach. This paper presents a proposal of a novel hybrid approach. A salient benefit of our system is that features provided from a text classifier and from an image classifier are combined appropriately to infer male or female gender using logistic regression. The experimentally obtained results demonstrate that our approach markedly improves an existing combination-based method.
Highlights
With rapid growth in social networking service (SNS), consumers increasingly use SNS to exchange and share their opinions related to products, services, politics, and other matters
Results confirmed that the p value is 0.0031, which indicates that the results obtained using our method are significantly better than those obtained using the existing combinationbased method
This paper presented a proposal for a novel hybrid approach
Summary
With rapid growth in SNS, consumers increasingly use SNS to exchange and share their opinions related to products, services, politics, and other matters. Many companies are motivated to use SNS data for marketing or advertisement to satisfy needs for improvements of their products or services in real time with low cost. In many cases, SNS user information such as gender, age or residence is not openly available, such information is extremely important for marketing. Several studies have been conducted to infer demographic information of anonymous users using text or image data posted on Twitter, and community membership (Rao and Yarowsky, 2010; Ikeda et al, 2013; Ma et al, 2014; Sakaki et al, 2014). We observed an important issue: each probability score output from the image classifiers and the text classifier was summed, the degree of their respective contributions to the inference is presumably different
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.