Telegram Users' Recommendation Based on the Membership Graph and Measuring Groups with Users from the Target Community

Telegram is a cloud-based messenger with more than 500 million monthly active users. Telegram's features include the creation of supergroups, channels, bots, and secret chats that provide users with more capabilities than a messenger. Telegram is used as a social network in Iran; but it does not offer all the features of a social network, including finding a collection of users. Finding users is very useful for marketers to find the target audience. In this paper, a method in two parts is presented by users' communication graph. The first part is based on graphs and model groups based on the percentage of subscriptions with incoming users. The second section ranks the groups based on the number of managers. The data of this study includes information about 70 million users and 700,000 supergroups in Telegram. The information obtained has been crawled by the IdeKav System, and it is worth noting that this information has been obtained quite legally by the tool provided by Telegram to the public. In this article, the proposed method is evaluated based on popular groups in Telegram. Popular groups are groups in which a single topic is discussed. In this paper, the evaluation by popular Telegram groups has been done by two categories of validation and test, and the results of experimental experiments have shown the repetition of the results and the integrity of the proposed method. The proposed method with the aim of covering the whole graph in two parts has shown the effectiveness of the suggestions and reduction of forecasting error compared to the previous three studies.