Labeled Dataset with extracted features

Technical question-answering sites like Stack Overflow are gaining enormous attention from the practitioners of specialized fields to exchange their programming knowledge. They ask questions on different topics, having various levels of difficulty and complexity. To answer such questions, all practitioners do not have the same level of expertise on those topics. However, the existing approach of Stack Overflow does not consider the difficulty and primarily filters out the questions based on topics only. For this reason, a large percentage of questions fail to attract the attention of appropriate users, resulting in questions having no answer or a significant delay in response time. To address these limitations, we incorporate three models, namely TF-IDF, LDA, and Doc2Vec, to extract semantic and context-dependent features that can measure the difficulty of questions. Each of these models is used with different classifiers along with other features to classify the questions based on difficulty. Extensive experiments on different datasets exhibit the effectiveness of our models, and the Doc2Vec outperforms the other models. We also discovered that the contextual features are correlated with question difficulty, and one subset of features outperforms others. The proposed approach can be beneficial for building an automatic tagger based on question difficulty.