科技資訊技術的日新月異,所有人都可以透過網際網路傳遞資訊,隨著網際網路上數據的增加,進而造成使用者在網際網路上尋找資訊的困難,產生了資訊超載的問題。目前可以透過資訊擷取與資訊過濾來解決使用者的困擾,透過使用者的瀏覽紀錄,進而主動向使用者推薦內容,節省使用者查詢的時間。本研究將以影片推薦為例,透過收集使用者的腦電波訊號,與影片相關評論進行結合,增加推薦項目的深度,推薦出更加符合使用者期待的項目。本研究運用羅吉斯迴歸建立腦波-偏好關聯模型,接著以自然語言處理來分析相關評論之情緒,再將兩者進行合併建立推薦系統,實驗結果顯示結合腦波訊號與影片評論情緒分析之推薦系統可以得到良好的推薦結果。
With advanced of Information Technology, everyone can upload and retrieve data on the Internet. There is too much data on the internet that make user is hard to find the necessary data on the internet. This issue is called Information Overloading. Through the recommender system recommend items for users can make users spending less time to find the necessary information on the internet. The recommender system collected the user’s behaviors, and by the user’s behaviors to recommend the items to the users they are interested in. In this research, we collected the brainwave signal by EEG and the comments from the videos, and then develop a recommender system based on the comment and EEG signals. Through this recommender system, the user can get the information more correspondingly. We used Logistic regression to construct the EEG-Preference model, and then combining with the analysis results that the comment’s sentiment by the Natural Language Processing. This recommender system will according to the user’s EEG-Preference model and the sentiment of the video’s comments to recommend the items to users. The experimental results show that the recommender system combined with brain wave signal and sentiment analysis of the videos’ comments can get good recommendation results.