Variability in answer quality, frequent question repetition, fragmented information, unstructured content, and the complexity of natural language are the primary issues in online video game forums. Unfortunately, traditional Q&A systems are inadequate for forum discussions due to their inability to process unstructured, contextual, and informal language. We propose the Pointer-Question-Filter-Game (PQF-Game), a novel language model designed for Restricted-Domain Question Answering Systems (RDQASs) in video game forums. In the answer recognition module of PQF-Game, we inserted a keyword filter pipeline using an attention-based Neural Matching Model (aNMM) to select relevant input keywords during similarity scoring. In the answer generation module, we integrated a question layer and a document layer within the Pointer-Generator architecture to improve semantic focus, reduce redundancy, and address out-of-vocabulary (OOV) issues. We evaluated our model using GameFAQs and Steam datasets. The PQF-Game achieved the highest ROUGE score, ROUGE-1 = 0.3372, ROUGE-2 = 0.1574, and ROUGE-L = 0.2658 when applying a 900-dimension skip-gram word embedding, compared to Pointer-Generator, Pointer-Gen + Cov, word-lvt5k-1sent, and state-of-the-art models, i.e., BART, T5, and PEGASUS. Although user input may contain typos, slang, or unseen words, the question layer successfully preserves the semantic aspect of the question and documents. Our proposed system demonstrates the ability to generate meaningful and accurate responses, as confirmed through human evaluation. Our key contribution lies in combining an aNMM-based keyword filtering pipeline with dual-attention mechanisms in the Pointer-Generator to enhance RDQASs performance.

This study is to evaluate whether peer evaluation increases student participation and thus improves learning achievement in an e-learning 2.0 environment. We first implemented an e-learning 2.0 platform and then collected data from student participants, including RSS, blogs, Wiki, and other online forums. A quasi-experimental design was used in the study. The student participants were divided into an experimental group (N=52) and a control group (N=60). The results indicated that the e-learning 2.0 platform had a positive effect on student learning process. When comparing the academic performances of the control group and the experimental group after using e-learning 2.0 for a period of time, students in the experimental group had significantly better academic results than those in the control group.

With Web 2.0 applications being widely used, social networking services, including web blogs, forums, and other online communities, have become informative tools that help individuals to easily gauge the pulse of the electronic consuming market. As a substitute for traditional public media, the related site provides unique mechanisms to instantly reveal the degree of public product acceptance by either statistically aggregating the rating results or archiving opinions shared by experienced customers. However, the growth of user-generated information and its scattered unstructured contents is overwhelming to users, thereby triggering the demand for a more efficient system that can offer concise information. Most existing efforts dedicated to these issues may neglect vital aspects of the sentence-level context. This article aims to explore the critical features hidden in the sentential structure of opinion articles and expects that the detected patterns may contribute to the enhancement of related applications. Accordingly, a multidimensional sentence modeling algorithm (MSMA) is designed to evaluate various sentential characteristics and adopt a genetic algorithm to optimize the weighting scheme while determining feature importance. The study also makes use of the public knowledge resource Wikipedia as a global reference to fine-tune the feature set's effectiveness and enhance the overall performance of this framework. The results of experiments on an electronic product data set demonstrate that the proposed method is promising and provides significant improvement over previous studies.

MOTIVATION: Transcriptional regulatory networks, which consist of linkages between transcription factors (TF) and target genes (TGene), control the expression of a genome and play important roles in all aspects of an organism's life cycle. Accurate prediction of transcriptional regulatory networks is critical in providing useful information for biologists to determine what to do next. Currently, there is a substantial amount of fragmented gene regulation information described in the medical literature. However, current related text analysis methods designed to identify protein-protein interactions are not entirely suitable for finding transcriptional regulatory networks. RESULT: In this article, we propose an automatic regulatory network inference method that uses bootstrapping of description patterns to predict the relationship between a TF and its TGenes. The proposed method differs from other regulatory network generators in that it makes use of both positive and negative patterns for different vector combinations in a sentence. Moreover, the positive pattern learning process can be fully automatic. Furthermore, patterns for active and passive voice sentences are learned separately. The experiments use 609 HIF-1 expert-tagged articles from PubMed as the gold standard. The results show that the proposed method can automatically generate a predicted regulatory network for a transcription factor. Our system achieves an F-measure of 72.60%. AVAILABILITY: The software, training/test datasets and learned patterns are available at http://140.116.99.138/∼hcw0901/PubMedSearch.php.