Online Web Forums Research Articles

The Impact of Parental Bereavement on Young People: A Thematic Analysis of Using Online Web Forums as a Method of Coping.

A qualitative approach was used to explore how online web forums might facilitate recovery and the process of coping. Ten online web forums written by young people who have personally experienced the death of a parent formed the data of this study. Previous research suggests forum users do not receive the supportive reactions from face-to-face interactions that they desire. Thematic analysis found that forums created an environment where young people can process the bereavement of a parent. Forums allowed young people to use their experience of bereavement to positively support others with similar experiences. The findings imply that the process of using forums can positively impact individuals who have experienced the loss of a parent. This supports recommendations by professionals, to consider online forums as a coping strategy. This study presents one of the few analyses of web forums written by young people who have experienced parental bereavement.

Aspect Based Online Sentiment Analysis Product Review and Feature Using Machine Learning

Today people, exchanging their thoughts through online web forums, blogs, and different platforms for social media. In online shopping, they are giving reviews and opinions on other various products, brands, and services. Their thoughts towards a product are do not only purchase decisions of the consumers but also improves the product quality about their requirements and find out the product's particular problem and get an excellent solution on that product. The present system concentrate on the peer-reviewed review model (User-generated review) and global qualification i.e., rating and, tries to classify the semantic aspect and emotions at the time aspect level from the data to investigate general sense feel of the reviews. SJASM represents each review document in the format of opinion pairs and, along with simulating the terms of appearance and the corresponding opinion words of the study, consideration for the hidden aspect and the sentiment detection. The current system is designed as a recommendation system Physiological Language Processing (NLP) Technique to read reviews and using Naïve Baye's Classification automatically. We have also extracted the thoughts of the product characteristics. Here admin can analyze the opinion pair that actually what is defect in the finished product so in future the market of that product will increase. This system to extract product aspects and corresponding opinions from consumer ratings on the internet. Different machine learning algorithms are discussed in Naïve Bayes is considered in order to classify of sentiments, and variables such as precision, recall, F-score, and accuracy are used to assess a classifier's performance.

Machine Learning Approach for Answer Detection in Discussion Forums: An Application of Big Data Analytics

Nowadays, data are flooding into online web forums, and it is highly desirable to turn gigantic amount of data into actionable knowledge. Online web forums have become an integral part of the web and are main sources of knowledge. People use this platform to post their questions and get answers from other forum members. Usually, an initial post (question) gets more than one reply posts (answers) that make it difficult for a user to scan all of them for most relevant and quality answer. Thus, how to automatically extract the most relevant answer for a question within a thread is an important issue. In this research, we treat the task of answer extraction as classification problem. A reply post can be classified as relevant, partially relevant, or irrelevant to the initial post. To find the relevancy/similarity of a reply to the question, both lexical and nonlexical features are used. We proposed to use LinearSVC, a variant of support vector machine (SVM), for answer classification. Two selection techniques such as chi-square and univariate are employed to reduce the feature space size. The experimental results showed that LinearSVC classifier outperformed the other state-of-the-art classifiers in the context of classification accuracy for both Ubuntu and TripAdvisor (NYC) discussion forum datasets.

Agency online: trends in a university learning course

This article aims to investigate how university students perform agency in an online course and whether the collaborative nature of the course affects such expression. A total of 11 online web forums involving 18 students (N = 745 posts in total) were qualitatively analysed through the use of a codebook composed of five categories (individual, interpersonal, epistemic, transformative and collective) and several sub-categories purposely developed for the sake of this research. The results show that each category follows a specific path, although two events – the re-mixing of the groups and the assumption of the peer-tutor role – particularly affected the evolution of trends. Although this study needs further development, the authors believe that an in-depth understanding of the nature of agency, including how to analyse it as well as empower it when implementing blended educational activities, engages relevant theoretical and pedagogical issues.