Improved binary crocodiles hunting strategy optimization for feature selection in sentiment analysis

Feature Selection (FS) for Sentiment Analysis (SA) becomes a complex problem because of the large-sized learning datasets. However, to reduce the data dimensionality, researchers have focused on FS using swarm intelligence approaches that reflect the best classification performance. Crocodiles Hunting Strategy (CHS), a novel swarm-based meta-heuristic that simulates the crocodiles' hunting behaviour, has demonstrated excellent optimization results. Hence, in this work, two FS algorithms, i.e., Binary CHS (BCHS) and Improved BCHS (IBCHS) based on original CHS were applied for FS in the SA field. In IBCHS, the opposition-based learning technique is applied in the initialization and displacement phases to enhance the search space exploration ability of the IBCHS. The two proposed approaches were evaluated using six well-known corpora in the SA area (Semeval-2016, Semeval-2017, Sanders, Stanford, PMD, and MRD). The obtained result showed that IBCHS outperformed BCHS regarding search capability and convergence speed. The comparison results of IBCHS to several recent state-of-the-art approaches show that IBCHS surpassed other approaches in almost all used corpora. The comprehensive results reveal that the use of OBL in BCHS greatly impacts the performance of BCHS by enhancing the diversity of the population and the exploitation ability, which improves the convergence of the IBCHS.