No abstract

Twitter is a renowned microblogging site that allows users to interact using tweets and it has almost reached 206 million daily active users by the second quarter of 2021. The ratio of Twitter bots has risen in tandem with their popularity. Bot detection is critical for combating misinformation and protecting the credibility of online disclosures. Current bot detection approaches rely on the Twitosphere’s topological structure, ignoring the heterogeneity among the profiles. Moreover, most techniques incorporate supervised learning, which depends strongly on large-scale training sets. Therefore, to overcome these issues, we proposed a novel entropy-based framework to detect correlated bots leveraging only user behavior. Specifically, real-time data of users is collected and their online behaviors are modeled as DNA sequences. We then determine the probability distribution of DNA sequences and compute relative entropy to evaluate the distance between the distributions. Accounts with entropy values less than a fixed threshold represent bots. Extensive experiments conducted in real-time Twitter data prove that the proposed detection technique outperforms state-of-the-art approaches with precision = 0.9471, recall = 0.9682, F1 score = 0.9511, and accuracy = 0.9457.

No abstract

Bug Triaging is a vital part of issue management systems. Bug triaging deals with assigning a developer the task of an incoming bug. This activity is error prone and time consuming if done manually. There is a need for automated support to accelerate this process. The current automated bug triaging systems exploits the text contents of the bug and the tossing relations among the developers. The automated bug triaging systems estimate the optimal bath between the first assignee of the bug and the bug resolver using the tossing relations. The metrics used for assessing the efficiency of bug triaging systems that are based on tossing relations is Mean number of Steps To Resolve (MSTR). This metric quantifies the number of steps reduced by the predicted path compared to the original path. It does not capture how far the retrieved path is in alignment with the actual path. MSTR does reveal the information regarding the extent to which the order of the developers in the retrieved path is in line with that of the original path. In addition, there are no indicators for measuring the strength of the retrieved path. In this paper, we propose two metrics (i) Path Similarity Metric which quantifies path alignment based on pair wise path alignment and (ii) Path Alignment Indicator that measures the effectiveness of the retrieved path based on degree centrality. The effectiveness of the two proposed metrics is validated using bug reports extracted from the Eclipse project.

No abstract