Faculty of Computing

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4202

Browse

Filters

2018 - 201912020 - 20221

Advanced Search

Filter by

Settings

Has files: YesSubject: search.filters.subject.Automate

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    PublicationEmbargo
    DevFlair: A Framework to Automate the Pre-screening Process of Software Engineering Job Candidates
    (IEEE, 2022-12-09) Jayasekara, R.T.R; Kudarachchi, K.A.N.D; Kariyawasam, K.G.S.S.K; Rajapaksha, D; Jayasinghe, S.L; Thelijjagoda, S
    The HR department of a technology company receives hundreds of job applications for each Software Engineering related vacancy. Evaluating a candidate by looking at the curriculum vitae may appear to be easy during the pre-screening process. However, an automated pre-screening process using Natural Language Processing and Machine Learning methodologies would help the recruiter to obtain a more accurate and deeper understanding of the candidate. In this paper we propose “DevFlair”, a framework to automate pre-screening Software Engineering job candidates. DevFlair uses data from social media, GitHub, and open-ended questionnaires to predict the Big-Five personality traits, analyze technical skill expertise, and analyze the experience in using industry-related online platforms. After analysis, the candidates are ranked according to their personality and technical skill levels. We conduct the personality prediction experiments using a social media posts dataset annotated with gold-standard Big-Five personality labels. We train FastText classification models and compare their accuracy against other state of the art classification models. The comparisons conclude that the FastText classification models substantially outperform the state of the art classification models when predicting Openness, Conscientiousness, and Agreeableness personality traits.
  • Thumbnail Image
    PublicationEmbargo
    An ontology-based approach to automate the software development process
    (IEEE, 2018-12-21) Athiththan, K; Rovinsan, S; Sathveegan, S; Gunasekaran, N; Gunawardena, K. S. A. W; Kasthurirathna, D
    Ontologies are well-known for representing knowledge of a particular domain and an upcoming trend in the field of Computer Science to produce intelligent systems. Further, they help to solve traceability issues and transitive dependencies. Creation of software applications and use of software applications are increased due to new and innovative customer requirements and technologies. Development teams are following several Software Development methodologies to support and to produce quality software applications to the outer world. Agile methodologies are becoming more popular in small organizations and development teams to support the feature by feature development with less throughput. User Stories represent the actual user requirements in Agile. This paper proposes a solution named Sponto, which to automate the software development process using ontology-based approaches to produce reliable boilerplates to the developers and the communities to reuse the base and to build the software applications without spending a considerable amount of time on recreating the artifacts. The proposed solution supports and generates database scripts, Business Process Model diagrams, Java code snippets, and test cases from user stories.