On June 24, 2018, Turkey conducted a highly consequential election in which the Turkish people elected their president and parliament in the first election under a new presidential system. During the election period, the Turkish people extensively shared their political opinions on Twitter. One aspect of polarization among the electorate was support for or opposition to the reelection of Recep Tayyip Erdoğan. In this paper, we present an unsupervised method for target-specific stance detection in a polarized setting, specifically Turkish politics, achieving 90% precision in identifying user stances, while maintaining more than 80% recall. The method involves representing users in an embedding space using Google's Convolutional Neural Network (CNN) based multilingual universal sentence encoder. The representations are then projected onto a lower dimensional space in a manner that reflects similarities and are consequently clustered. We show the effectiveness of our method in properly clustering users of divergent groups across multiple targets that include political figures, different groups, and parties. We perform our analysis on a large dataset of 108M Turkish election-related tweets along with the timeline tweets of 168k Turkish users, who authored 213M tweets. Given the resultant user stances, we are able to observe correlations between topics and compute topic polarization.
On June 24, 2018, Turkey conducted a highly consequential election in which the Turkish people elected their president and parliament in the first election under a new presidential system. During the election period, the Turkish people extensively shared their political opinions on Twitter. One aspect of polarization among the electorate was support for or opposition to the reelection of Recep Tayyip Erdogan. In this paper, we present an unsupervised method for target-specific stance detection in a polarized setting, specifically Turkish politics, achieving 90% precision in identifying user stances, while maintaining more than 80% recall. The method involves representing users in an embedding space using Google's Convolutional Neural Network (CNN) based multilingual universal sentence encoder. The representations are then projected onto a lower dimensional space in a manner that reflects similarities and are consequently clustered. We show the effectiveness of our method in properly clustering users of divergent groups across multiple targets that include political figures, different groups, and parties. We perform our analysis on a large dataset of 108M Turkish election-related tweets along with the timeline tweets of 168k Turkish users, who authored 213M tweets. Given the resultant user stances, we are able to observe correlations between topics and compute topic polarization.
Electronics and Computer Engineering"Creativity, problem solving, critical and analytical thinking, decision making, risk taking, all found in game-based learning.". Mark Grundel A Serious Game for Children with Speech Disorders and Hearing ProblemsNahid Nasiri AbstractSpeech impediment affecting children with hearing difficulties and speech disorders requires speech therapy and much practice to overcome. In fact, speech therapy via serious games gives an opportunity to children with speech disorders and hearing problems to overcome their problems. As far as children are more inclined to play games, so we intend to learn them by entertainments like serious games. In this thesis, we have designed and implemented a serious game that can be used both as a therapy and as a tool to measure the performance of children with speech impediments in which children will learn to speak specific words that they are expected to know before the age of 7. And then we will teach them how to make sentences. The game consists of three steps. The first step provides information for parents or therapists to decide if their child needs speech therapy or not. In the second step, the child starts to learn specific words while playing the game. The third step aims to measure the performance of the child and evaluate how much the child has learned at the end of the game. The game has an avatar which can be controlled by the child through speech, with the objective of moving the avatar around the environment to earn coins. The avatar is controlled by both voice commands such as Jump, Ahead, Back, Left, Right, and arrow keys of the keyboard. The child will be guided by an arrow during the game instead of getting help from a therapist or a teacher to guide the child to the next goal. This allows the child to practice longer hours, compared to clinical approaches under the supervision of a therapist, which are time-limited. Our preliminary performance measurements indicate an improvement of 40% for children who play our game at least 5 times and a specific period of time.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.