Abstract Online customer advocacy has developed as a distinctive strategic way to improve organisational performance by fostering favourable reciprocal affinitive customer behaviours between the business and its customers. Intelligent systems that can identify online social advocates based on their social interaction and long-standing conversations with the brads are still lacking. This study adds to the burgeoning body of literature in this research area by developing a novel model to identify brand advocates using natural language inference (NLI) and artificial intelligence (AI) approaches. In particular, a hybridised deep learning model (BERT-BiLSTM-TextCNN) is proposed and adept at extracting the amount of entailment, contradiction, and neutrality obtained from the advocates' replies to the brands. This offers a new dimension to identify advocates based on the semantic similarities between the brands’ tweets and customers’ replies. The experimental results demonstrate the applicability of integrating the advantages of fine-tuned BERT, TextCNN, and BiLSTM using various evaluation metrics. Further, the proposed model is incorporated in a downstream task to verify and validate its effectiveness in capturing the correlation between brands and their advocates. Our findings contribute to the burgeoning body of literature in this research area and have important implications for identifying and engaging with brand advocates in online customer engagement.

The phishing attack is one of the main cybersecurity threats in web phishing and spear phishing. Phishing websites continue to be a problem. One of the main contributions to our study was working and extracting the URL & Domain Identity feature, Abnormal Features, HTML and JavaScript Features, and Domain Features as semantic features to detect phishing websites, which makes the process of classification using those semantic features, more controllable and more effective. The current study used machine learning model algorithms to detect phishing websites, and comparisons were made. We have used 16 machine learning models adopted with 10 semantic features that represent the most effective features for the detection of phishing webpages extracted from two datasets. The GradientBoostingClassifier and RandomForestClassifier had the best accuracy based on the comparison results (i.e., about 97%). In contrast, GaussianNB and the stochastic gradient descent (SGD) classifier represent the lowest accuracy results; 84% and 81% respectively, in comparison with other classifiers.