Vietnam Journal of Computer Science

Reciprocal Recommender Systems (RRS) use bilateral preferences to satisfy the needs of both the parties involved. Popularity bias is a critical problem in RRS, which arises when the RRS tend to prefer few popular users over others and thus exhibit biased behavior towards popular users. It can have adverse effect on both the parties involved. Popular users may become swamped by the requests received from a large number of users and cease to acknowledge, which can make it difficult for other users to make contact. To address this challenge, we propose Popularity-aware Siamese Bi-directional Gated Recurrent Units (PSBiGRU) with the proposed popularity-aware reciprocal score (ParS)-based re-ranking that uses semantic similarity between explicit user profiles. The proposed model is evaluated on two reciprocal environments, namely, online recruitment and online dating. Experimental findings demonstrate that PSBiGRU surpasses the compared state-of-the-art methodologies and illustrate its viability.

Long Short-Term Memory (LSTM) Neural Network has great potential to predict sequential data. Time series prediction is one of the most popular experimental subjects of LSTM. To this end, various LSTM algorithms have been developed to predict time series data. However, there are a few works considering the hyperparameter optimization of LSTM along with parallelization approaches. To address this problem, a parallelized classic LSTM is proposed to predict time series. In the preprocessing phase, it first replaces missing values with zero and then normalizes the time series matrix. The transposed matrix is divided into training and testing parts. Consequently, a core-based parallelism is established, thereby utilizing forking to split prediction into multiple processes. Derivative-free optimization techniques are also analyzed to find out what sort of hyperparameter optimization technique is much more feasible for a parallelized LSTM. Further, a state-of-the-art comparison is included in the study. Experimental results show that training loss is optimal when using Nelder–Mead. Employing effort-intensive optimization methods such as genetic algorithms results in a remarkable CPU time reduction in parallelized designs according to the results. Last, the proposed algorithm outperformed the comparison methods with respect to the prediction errors.

The Bangla Language ranks seventh in the list of most spoken languages with 265 native and non-native speakers around the world and the second Indo-Aryan language after Hindi. However, the growth of research for tasks such as sentiment analysis (SA) in Bangla is relatively low compared to SA in the English language. It is because there are not enough high-quality publically available datasets for training language models for text classification tasks in Bangla. In this paper, we propose a Bangla annotated dataset for sentiment analysis on the ongoing Ukraine–Russia war. The dataset was developed by collecting Bangla comments from various videos of three prominent YouTube TV news channels of Bangladesh covering their report on the ongoing conflict. A total of 10,861 Bangla comments were collected and labeled with three polarity sentiments, namely Neutral, Pro-Ukraine (Positive), and Pro-Russia (Negative). A benchmark classifier was developed by experimenting with several transformer-based language models all pre-trained on unlabeled Bangla corpus. The models were fine-tuned using our procured dataset. Hyperparameter optimization was performed on all 5 transformer language models which include: BanglaBERT, XLM-RoBERTa-base, XLM-RoBERTa-large, Distil-mBERT and mBERT. Each model was evaluated and analyzed using several evaluation metrics which include: F1 score, accuracy, and AIC (Akaike Information Criterion). The best-performing model achieved the highest accuracy of 86% with 0.82 F1 score. Based on accuracy, F1 score and AIC, BanglaBERT outperforms baseline and all the other transformer-based classifiers.

The purpose of mining sequential patterns problem with weighted constraints is to find high-valued patterns, including infrequent patterns but having items which appear in the pattern of high importance in the sequence database (SD). Therefore, weighted sequential pattern mining will collect a set of more complete patterns with items of low support but of high importance. This paper proposes a new algorithm called WSPM_PreTree to find highly weighted sequential patterns. To collect a set of complete sequential patterns with the stricter weighted constraints of sequential patterns, the proposed algorithm uses both the minimum support constraint and the actual values of items appearing in the SD. To increase the performance of the finding weighted sequential patterns process, the algorithm uses the parent–child relationship on the prefix tree structure to create candidates and combines the weighted mean of the sequential 1-patterns that is calculated from the actual value of items in the SD as conditions to find the weighted sequential patterns. Experimental results show that the proposed algorithm is more efficient than sequential patterns mining with weight constraint (SPMW) algorithm [Ref. ] in the runtime.

In this study, we introduce a new synthetic data generation procedure for augmentation of histopathology image data. This is an extension to our previous research in which we proved the possibility to apply deep learning models for morphological analysis of tumor cells, trained on synthetic data only. The medical problem considered is related to the Ki-67 protein proliferation index calculation. We focused on the problem of cell counting in cell conglomerates, which are considered as structures composed of overlapping tumor cells. The lack of large and standardized data sets is a critical problem in medical image classification. Classical augmentation procedures are not sufficient. Therefore, in this research, we expanded our previous augmentation approach for histopathology images and we proved the possibility to apply it for a cell-counting problem.

In recent times, online users freely express their sentiments in different life aspects because of the huge increase in social networks. Sentiment Analysis (SA) is one of the main Natural Language Processing (NLP) fields thanks to its important role in identifying sentiment polarities and making decisions from the public’s opinions. The Arabic language is one of the most challenging languages for SA due to its various dialects, and morphological and syntactic complexities. Deep Learning (DL) models have shown significant capabilities, especially in SA. In particular, Long Short-Term Memory (LSTM) networks have proven perfect abilities to learn sequential data. This paper proposes a comparative study result of Word2Vec and FastText word embedding models that are used to create two Arabic SA (ASA) LSTM-based approaches. The experimental results confirm that the LSTM model with FastText can significantly ameliorate the Arabic classification accuracy.