ABSTRACT The continuous increase in news over the social web makes it difficult for users to search for a specific topic of interest. To overcome this difficulty, News Recommender Systems (NRS) are widely used to help users access the right and relevant content. Due to the diverse nature of NRS, researchers have started applying various deep learning (DL) models for the implementation of NRS. To our knowledge, however, current NRS do not look into the click‐through rate (CTR) with DL models. This manuscript proposes a news recommendation method that considers click‐log features with fine‐tuned DL models such as Artificial Neural Network (ANN), Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Long Short‐Term Memory (LSTM), and Gated Recurrent Unit (GRU) for news recommendation. The primary objective of this study is to recommend news to users by constructing a click‐rate matrix from the provided datasets. In this regard, the datasets are preprocessed, and then a user‐item matrix based on click‐through rate is constructed. To demonstrate the applicability of the click, log feature matrix with deep learning models for news recommendation, extensive experiments are conducted using two cross‐validation methods, namely K‐fold and holdout. We used precision, Area Under the Curve (AUC), and Normalized Discounted Cumulative Gain (nDCG) to test the performance of the proposed method. According to the results obtained, CNN performed better compared to other DL models. The evaluation results displayed that incorporating the click log feature matrix and DL models can significantly improve the news recommendation results. The study also suggests that the use of the click log feature matrix with DL models is the most effective and simple method for recommending news articles, outperforming the existing approaches.

With the recent advancements in conversational artificial intelligence (AI), the practical applications of chatbots have risen significantly in diverse domains such as healthcare, education, e-government, customer support systems, social platforms, and entertainment. The chatbot converses with humans in natural language and responds to their queries with precise and relevant answers. The relevant literature presents several methods for intent classification and slot mapping for chatbot question answering. However, the existing chatbot architectures still suffer from few-shot learning problem (imbalance ratio of class labels over samples) and ineffective dialog management to retain the context and slots mapping. This study aims to introduce the architecture of chatbot by focusing few-shot learning problem and context management in dialog-based conversations. First, to mitigate the few-shot learning problem with chatbots, we propose a novel hybrid intent and slots transformers (HIST) model. The HIST chatbot architecture utilizes transformers and self-attention mechanisms along with bigated recurrent unit and combines conditional random field algorithms for intent classification and slot extraction. Second, to address dialog management, we introduce a hybrid interaction strategy for slots mapping and effective conversational context management. To validate the proposed model’s effectiveness, comprehensive empirical analysis is carried out using three benchmark datasets including airline travel information system (ATIS), banking77, and conversational language interface for natural conversation 150 (CLINC150). The results show that HIST outperforms against the state-of-the-art existing methods with a clear margin and obtained an accuracy of 94.89% and 96.17% for intent classification and slots extraction, respectively. The empirical results confirm the effectiveness of the HIST chatbot for resolving the few-shot learning problem with effective dialog management in chatbot systems.

Social networks are online platforms that people use for interaction, information sharing and propagation of new ideas. Finding influential users in online social networks is a significant research problem due to its vast research applications in information diffusion, marketing and advertising. The relevant literature presents several models proposed for identifying influential users in social networks. In this survey, we present a review of the most relevant studies on influential users mining in microblog networks. First, we propose a new taxonomy by classifying the influence finding algorithms into five main categories based on their underlying framework and baseline methods. Second, each study is analysed according to the proposed framework, experimental datasets, validation approaches and evaluation results. Finally, the survey concludes with discussion on applications from the relevant literature, exploring open research challenges and presenting possible future research directions. The findings of this survey indicate that influential users mining in microblogs has many applications in marketing, advertising and information diffusion. In addition, this survey can be used as a guideline, particularly by young researchers, for establishing a baseline before initiating a research or identifying attractive as well as relevant research insights.

Sentiment Analysis (SA) is an active research area for the last ten years. SA is the computational treatment of opinions, sentiments, and subjectivity of text. Twitter is one of the most widely used micro-blog and considered as an important source for computation of sentiment and of data analysis. Therefore, companies all over the world analyze Twitter data using SA and extract knowledge which has potential applications in diverse areas. Although SA is the successful way of finding the people’s opinion, the bias in the tweets affects the results of the SA and reflects inaccurate analysis that may mislead users to take erroneous decisions. The biased tweets are shared by valid, but biased human users as well as the social bots to propagate the biased opinions on certain topics. To counter this, this research study proposes a statistical model to identify such users and social bots who share the biased content in the form of tweets in the Twitter social media. For experiment purpose, we use annotated twitter dataset and argue the results of SA with and without the biased tweets and explored the effects of biased users at micro-level and macro level. The empirical results show that the proposed approach is effective and properly identifies the biased users and bots from other authentic users using sentiment analysis.