Hate speech detection has substantially increased interest among researchers in the domain of natural language processing (NLP) and text mining. The number of studies on this topic has been growing dramatically. Thus, the purpose of this analysis is to develop a resource that consists of an outline of the approaches, methods, and techniques employed to address the issue of Twitter hate speech. This study can be used to aid researchers in the development of a more effective model for future studies. This review focused on studies published over the past eight years, i.e., from 2015 to 2022. This systematic search was carried out in December 2020 and updated in July 2022. Ninety-one articles published within the mentioned period met the set criteria and were selected for this review. From the evaluation of these works, it is clear that a perfect solution has yet to be found. To conclude, this paper focused on presenting an in-depth understanding of current perspectives and highlighted research opportunities to boost the quality of hate speech detection systems. In turn, this helps social networking services that seek to detect hate messages generated by users before they are posted, thus reducing the risk of targeted harassment.

No abstract

Funding Acknowledgements Type of funding sources: Other. Main funding source(s): Solve CHD NHMRC Synergy Grant Background Spontaneous coronary artery dissection (SCAD) is estimated to account for 4% of acute coronary syndrome presentations but is a distinctly different disease and demographic from typical atherosclerotic heart attacks. Survivors of SCAD typically turn to the internet for information. However, websites are not subject to stringent quality regulation. Purpose This study identified and appraised websites containing SCAD information using a variation of a systematic review study design. Quality, suitability, readability and content accuracy and scope were assessed. Methods Keywords related to SCAD definition, rarity, treatment, support and life after SCAD were searched in Google. Results were screened and evaluated systematically. Information content was assessed using a point-scoring tool based on current SCAD consensus literature. Quality and suitability of the websites was assessed using the Suitability Assessment of Materials, Quality Component Scoring System (QCSS), the Health-Related Website Evaluation Form (HRWEF), and adherence to the Health on the Net code. Readability was assessed using the Simple Measure of Gobbledygook, Flesch-Kincaid, and a readability generator. Results Of the 600 screened, n=316 duplicates were removed and n=50 eligible websites were included. Websites were most frequently made by hospital groups (34%), independent organisations (20%) and survivors (24%). The most frequent grading of quality was poor (32%) or good (30%) using the QCSS and adequate using the HRWEF (74%). Suitability of materials was overall adequate (64%). Content, scope and depth across websites had a mean score of 47.5 (SD 25.0) and was rated poor. The websites with highest scores for factually accurate content were survivor made (57.9%) and national foundations (56.3%) versus professional associations (34.6%) and hospital groups (35.2%) which had the lowest. The emotional impact of SCAD was addressed in 52% and content regarding family or partners support was given in 40%. Survivors had input in 63% and survivor groups were recommended in 50%. Most websites were rated fairly difficult (46%) or difficult to read (42%), with a mean readability grade of 11.6 (SD 2.3). Conclusions Despite high availability and fair quality, websites for SCAD survivors to access have poor content depth and require higher reading proficiency to understand. Almost half neglect the emotional impact of SCAD on the survivor and their families. Given the generally poor content of information available online, it is essential that SCAD survivors are provided high quality information on discharge from hospital and during cardiac rehabilitation. Health authority website are considered authoritative sources and for SCAD need to be improved. Survivor and national foundation websites may be the most appropriate to recommend for SCAD information currently due to higher factually correct content scores, broader scope of information, and demographically contextual material.