No abstract

No abstract

No abstract

PurposeHate speech is an expression of intense hatred. Twitter has become a popular analytical tool for the prediction and monitoring of abusive behaviors. Hate speech detection with social media data has witnessed special research attention in recent studies, hence, the need to design a generic metadata architecture and efficient feature extraction technique to enhance hate speech detection.Design/methodology/approachThis study proposes a hybrid embeddings enhanced with a topic inference method and an improved cuckoo search neural network for hate speech detection in Twitter data. The proposed method uses a hybrid embeddings technique that includes Term Frequency-Inverse Document Frequency (TF-IDF) for word-level feature extraction and Long Short Term Memory (LSTM) which is a variant of recurrent neural networks architecture for sentence-level feature extraction. The extracted features from the hybrid embeddings then serve as input into the improved cuckoo search neural network for the prediction of a tweet as hate speech, offensive language or neither.FindingsThe proposed method showed better results when tested on the collected Twitter datasets compared to other related methods. In order to validate the performances of the proposed method, t-test and post hoc multiple comparisons were used to compare the significance and means of the proposed method with other related methods for hate speech detection. Furthermore, Paired Sample t-Test was also conducted to validate the performances of the proposed method with other related methods.Research limitations/implicationsFinally, the evaluation results showed that the proposed method outperforms other related methods with mean F1-score of 91.3.Originality/valueThe main novelty of this study is the use of an automatic topic spotting measure based on naïve Bayes model to improve features representation.

Dynamic Guard Channels (DCG) reduces the dropping and blocking rates in a network. However, most of the existing DGC allocations are not quite efficient because there were consideration for only the Handoff (HO) calls while the New calls (NC) were not considered; this leads to poor Quality of Service (QoS) for NC. Although it is better to give priority to HO calls over NC since the breaking of the connection of an established communicationis more annoying than blocking a NC. Thus, there is need to provide an alternative approach that guarantees an acceptable QoS in terms of both the HC and the NC. This paper presents the performance evaluation of an adaptive guard channel allocation; the scheme made use of two different models (1) guard channel with fuzzy logic (2) guard channel without fuzzy logic. Priority is given to handoff call due to the scarcity of radio spectrum. When all the guard channels have been allocated and the arrival rate of handoff calls keeps on increasing, new set of threshold values would be estimated by fuzzy logic model. Performance metrics are; Call Blocking Rate (CBR), Call Dropping Rate (CDR) and Throughput. Results showed that guard channel with fuzzy logic has the CBR values range from 24.02% to 69.015 and CDR values range from 12.025 to 18.90% while guard channel without fuzzy logic has CBR values range from 28.22% to 75.65% and CDR values range from 19.06% to 36.50%. The scheme proved to be more efficient in congestion control in wireless network.