Browsing by Author "Chen, Li-Xian"

Now showing 1 - 3 of 3

A Photo Post Recommendation System Based on Topic Model for Improving Facebook Fan Page Engagement
(2020-07-01)
Liao, Chia-Hung
;
Chen, Li-Xian
;
Yang, Jhih-Cheng
;
Yuan, Shyan-Ming
;
資訊工程學系
Digital advertising on social media officially surpassed traditional advertising and became the largest marketing media in many countries. However, how to maximize the value of the overall marketing budget is one of the most concerning issues of all enterprises. The content of the Facebook photo post needs to be analyzed effectively so that the social media companies and managers can concentrate on handling their fan pages. This research aimed to use text mining techniques to find the audience accurately. Therefore, we built a topic model recommendation system (TMRS) to analyze Facebook posts by sorting the target posts according to the recommended scores. The TMRS includes six stages, such as data preprocessing, Chinese word segmentation, word refinement, TF-IDF word vector conversion, creating model via Latent Semantic Indexing (LSI), or Latent Dirichlet Allocation (LDA), and calculating the recommendation score. In addition to automatically selecting posts to create advertisements, this model is more effective in using marketing budgets and getting more engagements. Based on the recommendation results, it is verified that the TMRS can increase the engagement rate compared to the traditional engagement rate recommended method (ERRM). Ultimately, advertisers can have the chance to create ads for the post with potentially high engagements under a limited budget.
Associations among scaffold presentation, reward mechanisms and problem-solving behaviors in game play
(2018-04-01)
Sun, Chuen-Tsai
;
Chen, Li-Xian
;
Chu, Hsiu-Mei
;
資訊工程學系
;
Department of Computer Science
Learning assistance tools used with digital games commonly called scaffolds can reduce player frustration and help them create problem-solving strategies while supporting achievement. Reward mechanisms in the form of external incentives are also believed to enhance motivation and promote learning, but possibly at the expense of excessive learner reliance. Some researchers have suggested that reward mechanisms can be used to discourage players from becoming dependent on scaffolds. For this study we customized Professor Sudoku, a simplified version of the popular digital reasoning game, to investigate the effects of scaffold presentation-plus-reward mechanism on problem-solving behaviors and actions aimed at leveling-up. A total of 126 participants were divided into active scaffold (providing direct assistance to players at the beginning of a game), passive scaffold (provided by the game system when players made three mistakes within a specified time frame), and hidden scaffold groups (accessible at any time). Each scaffold served three functions: critical feature marking, frustration control, and demonstration. The three groups were given point-gain and point-loss reward mechanisms. Our data indicate that the appropriate presentation of one or more scaffolds reduced player reliance on support, thereby increasing the potential for positive learning effects and reducing frustration. Results suggest that the reward mechanism promoted independent problem solving instead of reliance on scaffolds, and that the addition of scaffolds and reward mechanisms encouraged experienced players to create new rules, overcome the limitations of existing rules, and develop more complex learning strategies. We discuss the need to carefully design scaffold presentation type according to specific instructional purposes, and possible benefits for teachers in terms of analyzing the difficulties that individual students face when solving numerical problems.
Self-regulation influence on game play flow state
(2016-01-01)
Chen, Li-Xian
;
Sun, Chuen-Tsai
;
資訊工程學系
;
Department of Computer Science
The authors use the Music Flow digital game with 266 Taiwanese junior high school students to investigate the influence of digital game player self-regulation (SR) on game flow state. Game data were used to probe various aspects of Bandura\'s (1986) SR learning model and related effects on game flow state as described in Csikszentmihalyi\'s (1990) flow theory to determine if game information can be used to measure SR during different flow states. A tool for recording stage selection, hit rate, and other real time data was created to monitor and measure flow state among players immersed in interactive play. Self-reaction capabilities were measured in terms of skill- and game-level difficulty during different states. Results indicate that SR exerted a significant and positive effect on flow state. Our main conclusions are (a) flow state was continuously influenced by self-reaction over time; (b) hit rate served as an indicator of self-judgment in terms of challenge, skill and flow state; and (c) flow states in players with distinct self-reaction capabilities were influenced by play stage selection. It is our hope that the method used in this study will help researchers in their efforts to measure and/or analyze player sense of fun in game-based learning environments. (C) 2015 Elsevier Ltd. All rights reserved.