Automatic Topic detection seems unavoidable in social media analysis due to big text data which their users generate. Clustering-based methods are one of the most important and up-to-date categories in Topic detection. The goal of this research is to have a wide study on this category. Therefore, this paper aims to study the main components of clustering-based-Topic-detection, which are embedding methods, distance metrics, and clustering algorithms. Transfer learning and consequently pretrained language models and word embeddings have been considered in recent years. Regarding the importance of embedding methods, the efficiency of five new embedding methods, from earlier to recent ones, are compared in this paper. To conduct our study, two commonly used distance metrics, in addition to five important clustering algorithms in the field of Topic detection, are implemented by the authors. As COVID-19 has turned into a hot trending Topic on social networks in recent years, a dataset including one-month tweets collected with COVID-19-related hashtags is used for this study. More than 7500 experiments are performed to determine tunable parameters. Then all combinations of embedding methods, distance metrics and clustering algorithms (50 combinations) are evaluated using Silhouette metric. Results show that T5 strongly outperforms other embedding methods, cosine distance is weakly better than other distance metrics, and DBSCAN is superior to other clustering algorithms.

Research in the field of video surveillance systems has been improving because of the increasing need for intelligent monitoring, control and management. Given the large amount of data on these intelligent transportation systems, extracting patterns and automatically labeling them is a challenging task. In this paper, a Topic model was used to detect and extract traffic patterns at intersections so that visual patterns are transformed into visual words. The input video is first split into clips. Then, the flow characteristics of the clips, which are based on abundant local motion vector information, are computed using optical flow algorithms and converted to visual words. After that, with a non-probabilistic Topic model, the traffic patterns are extracted to the designed system by a group sparse Topical coding method. These patterns represent visible motion that can be used to describe a scene by answering a behavioral question such as: Where does a vehicle go? The results of the implementation of the proposed method on the QMUL video database show that the proposed method can correctly detect and display meaningful traffic patterns such as turn left, turn right and crossing a roundabout.

Short texts of social media like Twitter provide a lot of information about hot Topics and public opinions. For better understanding of such information, Topic detection and tracking is essential. In many of the available studies in this field, the number of Topics must be specified beforehand and cannot be changed during time. From this perspective, these methods are not suitable for increasing and dynamic data. In addition, non-parametric Topic evolution models lack appropriate performance on short texts due to the lack of sufficient data. In this paper, we present a new evolutionary clustering algorithm, which is implicitly inspired by the distance-dependent Chinese Restaurant Process (dd-CRP). In the proposed method, to solve the data sparsity problem, social networking information along with textual similarity has been used to improve the similarity evaluation between the tweets. In addition, in the proposed method, unlike most methods in this field, the number of clusters is calculated automatically. In fact, in this method, the tweets are connected with a probability proportional to their similarity, and a collection of these connections constitutes a Topic. To speed up the implementation of the algorithm, we use a cluster-based summarization method. The method is evaluated on a real data set collected over two and a half months from the Twitter social network. Evaluation is performed by clustering the texts and comparing the clusters. The results of the evaluations show that the proposed method has a better coherence compared to other methods, and can be effectively used for Topic detection from social media short texts.

The emergence of social media creates opportunities for users to share their thoughts. Billions of short texts are produced on social media daily, and their analysis in text mining and content analysis is essential. Detecting Topics from short texts on a large scale is an important and challenging task. Few studies have been conducted on Topic detection in Persian short texts, and the existing algorithms are not remarkable. Therefore, we decided to study the Topic detection in Persian. Topic modeling is a Topic detection technique that extracts groups of words as Topics from documents. Recently, neural Topic models have shown improvements in increasing the coherence of Topic modeling. Also, text embeddings have enhanced neural models. For this reason, in this study, two combined Topic models and the ZeroShot Topic model are presented for Topic detection in Persian social media short texts. These two models incorporate pre-trained BERT text representation into neural Topic models. The experimental results show that these two methods outperform the comparison methods with the highest F1-measure, Topic diversity, and coherence score. Also, the ZeroShot Topic model has better results in terms of evaluation metrics than the combined Topic model

Metalepsis, in its narratological sense, is a trope in which an unnatural relationship is built between different levels of narrative. The natural relationship between narrative levels is formed by the act of narrating; a character from one level becomes the narrator of another. The term “ Metalepsis of Topic and illustration” can be coined to name a similar trope. This trope has been used for centuries in Persian poetry. Every Image comprises a Topic and an illustration. The Topic is what is being talked about and the illustration is what the Topic is compared to. When several images are present along together, two different levels are distinguishable: the level of the Topic and the level of illustration. The natural relationship between these two levels is similarity and any other relationship will result in metalepsis. As in the narratological metalepsis, there is always a paradox in the metalepsis of Topic and illustration. The effect of these two kinds of metalepsis is also similar and can be humorous, fantastic, or a mixture of the two.

This paper investigates text documents regarding their Topic density. It has divided them into two groups: dense and sparse documents. Dense documents are texts with a wide domain of Topics. They have a high Topic density (for example religious books, encyclopedia, magazine archives, etc ). We have shown that a) traditional methods cannot be used for Topic specific of dense texts, and b) we can benefit from employing the efficiency of the proposed method (Nasir) for dense texts.In this research, we have used dependency relations, paths, triple databases and statistical text processing methods to extract important words and to insert them into a clustering index. Also a method was described to find the reference of pronouns in dense texts. In addition, based on the suggested methods, a prototype system called Nasir was implemented. The result of the implementation on Persian dense texts shows that the quality of indexing and searching improved significantly.