Social media platforms influence the way political campaigns are run and
therefore they have become an increasingly important tool for politicians to
directly interact with citizens. Previous elections in various countries have
shown that social media data may significantly impact election results. In this
study, we aim to predict the vote shares of parties participating in the 2023
elections in Turkey by combining social media data from various platforms
together with traditional polling data. Our approach is a volume-based approach
that considers the number of social media interactions rather than content. We
compare several prediction models across varying time windows. Our results show
that for all time windows, the ARIMAX model outperforms the other algorithms.

通过结合社交媒体数据及传统投票数据，我们采用基于交互量的方法，比较多种算法在不同时窗口下预测土耳其 2023 年选举党派得票份额，结果发现，在所有时间窗口下，ARIMAX 模型表现最佳。

利用社交媒体数据预测 2023 年土耳其总统选举结果

Prediction of the 2023 Turkish Presidential Election Results Using  Social Media Data

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 Erdo\u{g}an. 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.

本文利用卷积神经网络对土耳其大选期间推特数据进行无监督的极性检测，对 108M 条推文和 213M 条用户推特进行多目标分类和极性聚类，实现用户态度识别和相关话题极化计算。