Trend-Based Categories Recommendations and Age-Gender Prediction for Pinterest and Twitter Users

Abstract

Category suggestions or recommendations for customers or users have become an essential feature for commerce or leisure websites. This is a growing topic that follows users’ activity in social networks generating a huge quantity of information about their interests, contacts, among many others. These data are usually collected to analyze people’s behavior, trends, and integrate a complete user profile. In this sense, we analyze a dataset collected from Pinterest to predict the gender and age by processing input images using a Convolutional Neural Network. Our method is based on the meaning of the image rather than the visual content. Additionally, we propose a heuristic-based approach for text analysis to predict users’ age and gender from Twitter. Both of the classifiers are based on text and images and they are compared with various similar approaches in the state of the art. Suggested categories are based on association rules conformed by the activity of thousands of users in order to estimate trends. Computer simulations showed that our approach can recommend interesting categories for a user analyzing his current interest and comparing this interest with similar users’ profiles or trends and, therefore, achieve an improved user profile. The proposed method is capable of predicting the user’s age with high accuracy, and at the same time, it is able to predict gender and category information from the user. The certainty that one or more suggested categories be interesting to people is higher for those users with a large number of publications.

Predicting user demographics based on interest analysis

“…In the next step, to compare our work with other studies, we reduce the number of age classes to three. Yumeng Li et al [21], Ibrahim Mousa Al-Zuabi et al [6] get an accuracy of 0.65 for the three age groups, and Roberto Garcia-Guzman et al [12] has an accuracy of 0.67 for the same number of age groups. In our study, by reducing the age groups from 7 to 3 categories, the accuracy of the MLP algorithm in the first method -i.e., using popular items ratings -has achieved an accuracy of 0.65%.…”

“…To predict the demographic information, previous works [12,24,23,19,20,31,9,6,21,7,16,22] employ all data generated by users. On the other hand, information extraction based on users interests seems to be challenging as data is massive and time-varying.…”

“…Moreover, by restricting ratings to those recorded for popular movies (which include 5% of all movies), we acquire an accuracy of 60% for age prediction. Furthermore, we determine user's gender by using ratings that are registered for popular movies and the accuracy is improved almost 8% compared with a recent gender prediction [12]. For a more detailed discussion regarding the metrics we refer the reader to Subsection 3.4.…”

“…Li et al [21] design an attentionbased neural network to identify features such as age, gender, and geographic location by extracting the meanings of texts published by users and social network information. Garcia et al [12] developed two models for determining a user's age and gender. The first model is based on textual information posted by users on Twitter and the other one is based on the category of photos that users have posted on Pinterest.…”

Inferring Ties in Social IoT Using Location-Based Networks and Identification of Hidden Suspicious Ties

“…A social network such as Twitter forms a bidirectional graph, e.g., a fan follows a celebrity but the celebrity hardly ever follows back. Usage of bidirectional graphs investigates influential networks and most inflectional people [17][18][19]. Recommendation and targeted marketing are some of the essential objectives of exploring social ties [20,21].…”