With the widespread use of social networks, detecting the topics discussed in
these networks has become a significant challenge. The current works are mainly
based on frequent pattern mining or semantic relations, and the language
structure is not considered. The meaning of language structural methods is to
discover the relationship between words and how humans understand them.
Therefore, this paper uses the Concept of the Imitation of the Mental Ability
of Word Association to propose a topic detection framework in social networks.
This framework is based on the Human Word Association method. The performance
of this method is evaluated on the FA-CUP dataset. It is a benchmark dataset in
the field of topic detection. The results show that the proposed method is a
good improvement compared to other methods, based on the Topic-recall and the
keyword F1 measure. Also, most of the previous works in the field of topic
detection are limited to the English language, and the Persian language,
especially microblogs written in this language, is considered a low-resource
language. Therefore, a data set of Telegram posts in the Farsi language has
been collected. Applying the proposed method to this dataset also shows that
this method works better than other topic detection methods.

本论文提出一种基于 Word Association 的社交网络话题检测框架，利用语言结构方法发现单词间的关系，结合人类 Word Association 模型实现更好的效果，在英语和波斯语低资源语言中进行测试，显示出良好的性能。

一种基于人类词语联想的社交网络主题检测模型

A Human Word Association based model for topic detection in social networks

Speech Emotion Recognition (SER) is of great importance in Human-Computer
Interaction (HCI), as it provides a deeper understanding of the situation and
results in better interaction. In recent years, various machine learning and
Deep Learning (DL) algorithms have been developed to improve SER techniques.
Recognition of the spoken emotions depends on the type of expression that
varies between different languages. In this paper, to further study important
factors in the Farsi language, we examine various DL techniques on a
Farsi/Persian dataset, Sharif Emotional Speech Database (ShEMO), which was
released in 2018. Using signal features in low- and high-level descriptions and
different deep neural networks and machine learning techniques, Unweighted
Accuracy (UA) of 65.20% and Weighted Accuracy (WA) of 78.29% are achieved.

本研究利用各种深度学习和机器学习技术，通过对一个 Farsi/Persian 数据集的分析，研究了 Farsi 语言中的情感识别技术，取得了 65.20% 的 UA 和 78.29% 的 WA。