結合腦波分析與內容導向過濾為基礎的文章推薦系統

A Document Recommendation System Based on Content-based Filtering and Brainwave

陳灯能(Deng-Neng Chen)；蘇柏銘(Po-Ming Su)

腦波 ； 神經資訊學 ； 文章推薦系統 ； 內容導向過濾 ； 類神經網路 ； brainwave ； NeuroIS ； document recommender system ； content-based filtering ； neural network

資訊管理學報

22卷2期（2015 / 04 / 01）

141 - 170

繁體中文

推薦系統是一種基於使用者紀錄或偏好進行資料收集及分析，藉此分析結果逕行主動式資訊推薦的資訊系統，推薦系統在提昇個人化資訊服務品質上扮演重要的角色。傳統上推薦系統的設計著重於將資料庫中使用者的相關記錄進行分析，也因此衍生出內容導向、協同導向等不同演算法為基礎的推薦系統，在神經資訊學中，則是認為資訊系統的開發可以結合神經科學的理論與工具，以更貼近人類認知行為模式來開發資訊系統，也因此本研究嘗試將使用者的腦波訊號納入推薦系統的演算法設計之中，期望能提供更貼近使用者偏好的推薦服務。腦波是一種生物訊號，是人們大腦在進行某種活動時自然產生的一種訊號，可透過腦電波儀進行量測。本研究首先以實驗法收集受測者腦波訊號與其興趣偏好資料，並利用類神經網路建立腦波與使用者偏好之間的關聯模型，進而以此關聯資訊為核心，開發一套結合腦波與內容導向資訊過濾為基礎的文章推薦系統，最後並以實驗法驗證本推薦系統的推薦精準度。研究結果發現，本研究所開發的文章推薦系統能確實提昇推薦精準度，也證明了腦波能夠有效的被利用在推薦系統的設計上。

Purpose-Recommender system is an information system that can recommend the most appropriate information to the user. In a recommender system, the user's logs and preferences are collected and analyzed to figure out the user's profile that can be used to develop the system. Brainwave is a kind of biological signal that can be used to indicate different mental condition of a human. In this research, we applied the brainwave information to identify the attention level of the experimental subjects to design and implement a document recommender system. Design/methodology/approach-We applied electroencephalography (EEG) to collect the brainwave information, and the association model between users' brainwaves and preferences were constructed by neural network. In advance, the brainwave-preference model was applied to develop a document recommender system. We have also conducted an experiment to evaluate the effectiveness of our recommender system. Findings-The results show that the recommender system based on brainwave-preference model has better recommendation precision rate than the traditional content-based recommender system. Brainwave can play an important role in the development of recommender systems. Research limitations/implications-Due to the limitation of unstable brainwave information collected in the experiment, it is difficult to request the experimental subjects to read more documents as the training data, and effective experimental samples are also limited. By the advance of EEG and neuroscience, the measuring of brainwave will be getting more precise and stable and the development of brainwave-based information systems will be more feasible. Practical implications-We have designed and implemented a brainwave-based recommender system in our research. The system architecture can be used in the developments of other information systems, such as merchandises recommender systems in e-stores. With the advance of wearable technology, the EEG will be getting more popular, and more brainwave-based information systems will be developed and applied. Originality/value-We have highlighted a new research direction to design the recommender systems based on brainwave. With the development of NeuroIS, the applications of neuroscience in information systems research is getting popular. Our research provides a new methodology to design a brainwave-based information systems, and it is contributive to NeuroIS.

1. Blair, A. (2010),' Information Overload, Then and Now', The Chronicle Review,available at http://chronicle.com/article/Information-Overload-Then-and/125479/ (accessed 14 October 2014).
2. Balabanović, M.,Shoham, Y.(1997).Fab: Content-based, collaborative recommendation.Communications of the ACM,40(3),66-72.
3. Bobadilla, J.,Ortega, F.,Hernando, A.,Gutiérrez, A.(2013).Recommender systems survey.Knowledge-Based Systems,46,109-132.
4. Brusilovsky, P.(Ed.),Kobsa, A.(Ed.),Nejdl, W.(Ed.)(2007).The Adaptive Web: Methods and Strategies of Web Personalization.New York:Springer Verlag.
5. Brusilovsky, P.,Kobsa, A.,Nejdl, W.(2007).The Adaptive Web: Methods and Strategies of Web Personalization.New York:Springer Verlag.
6. Cacioppo, J.T.(Ed.),Tassinary, L.G.(Ed.),Berntson, G.(Ed.)(2007).Handbook of Psychophysiology.New York:Cambridge University Press.
7. Chang, C.Y.,Lo, C.Y.,Wang, C.J.,Chung, P.C.(2010).A music recommendation system with consideration of personal emotion.Proceedings of the International Computer Symposium (ICS),Taian, Taiwan:
8. de Guinea, A.O.,Titah, R.,Léger, P.M.(2014).Explicit and implicit antecedents of users' behavioral beliefs in information systems: A neuropsychological investigation.Journal of Management Information Systems,30(4),179-210.
9. Dimoka, A.(2010).What does the brain tell us about trust and distrust? Evidence from a functional neuroimaging study.MIS Quarterly,34(2),373-396.
10. Dimoka, A.,Pavlou, P.,Davis, F.(2007).Neuro-IS: the potential of cognitive neuroscience for information systems research.Proceedings of the International Conferenceon Information Systems(ICIS),Montreal, Canada:
11. Doomen, J.(2009).Information Inflation.Journal of Information Ethics,18(2),27-37.
12. Gerrard, P.,Malcolm, R.(2007).Mechanisms of modafinil: a review of current research.Neuropsychiatric Disease and Treatment,3(3),349-364.
13. Gregor, S.,Lin, A.C.,Gedeon, T.,Riaz, A.,Zhu, D.(2014).Neuroscience and a nomologicalnetwork for the understanding and assessment of emotions in information systems research.Journal of Management Information Systems,30(4),13-48.
14. Hughes, J.R.(2008).Gamma, fast, and ultrafast waves of the brain: their relationships with epilepsy and behavior.Epilepsy & Behavior,13(1),25-31.
15. Kuan, K.K.Y.,Zhong, Y.,Chau, P.Y.K.(2014).Informational and normative social influence ingroup-buying: evidence from self-reported and EEG data.Journal of Management Information Systems,30(4),151-178.
16. Liang, T.P.(2012).Cognitive Neuroscience in Information Systems Research.Pacific Asia Journal of the Association for Information Systems,4(1),1-3.
17. Liang, T.P.,Yang, Y.F.,Chen, D.N.,Ku, Y.C.(2008).A semantic-expansion approach to personalized knowledge recommendation.Decision Support Systems,45(3),401-412.
18. Michel, C.M.,Henggeler, B.,Brandeis, D.,Lehmann, D.(1993).Localization of sources of brain alpha/theta/delta activity and the influence of the mode of spontaneous mentation.Physiological Measurement,14(4A),A21-A26.
19. Minas, R.K.,Dennis, A.R.,Potter, R.F.,Bartelt, V.,Bae, S.(2014).Putting on the thinking cap: Using NeuroIS tounderstand information processing biases in virtual teams.Journal of Management Information Systems,30(4),49-82.
20. Rangaswamy, M.,Porjesz, B.,Chorlian, D.B.,Wang, K.,Jones, K.A.,Bauer, L.O.,Rohrbaugh, J.,O'Connor, S.J.,Kuperman, S.,Reich, T.,Begleiter, H.(2002).Beta power in the EEG of alcoholics.Biol Psychiatry,52(8),831-842.
21. Riedl, R.,Banker, R.D.,Benbasat, I.,Davis, F.D.,Dennis, A.R.,Dimoka, A.,Gefen, D.,Gupta, A.,Ischebeck, A.,Kenning, P.,Müller-Putz, G.,Pavlou, P.A.,Straub, D.W.,vomBrocke, J.,Weber, B(2010).On the Foundations of NeuroIS: Reflections on the Gmunden Retreat 2009.Communications of the Association for Information Systems,27(1),243-264.
22. Riedl, R.,Hubert, M.,Kenning, P.(2010).Are there neural gender differences in online trust? An fMRI study on the perceived trustworthiness of eBay offers.MIS Quarterly,34(2),397-428.
23. Salton, G.(1989).Automatic text processing: the transformation, analysis, and retrieval of information by compute.Boston:Addison-Wesley.
24. Shih, Y.Y.,Liu, D.R.(2008).Product recommendation approaches: Collaborative filtering via customer lifetime value and customer demands.Expert Systems with Applications,35(1),350-360.
25. Vom Brocke, J. ,Liang, T.P.(2014).Guidelines for Neuroscience Studies inInformation Systems Research.Journal of Management Information Systems,30(4),211-234.
26. Wang, X.J.(2010).Neurophysiological and computational principles of cortical rhythms in cognition.Physiol reviews,90(3),1195-1268.

1. 陳志達(2022)。專利知識本體之建立與推薦系統。資訊與管理科學，15(1)，4-19。
2. 蘇芳儀,楊文淵,邱兆民(2022)。應用刺激－有機體－反應理論與心流理論以探討Instagram限時動態使用者黏著度之影響因素。資訊管理學報，29(4)，397-432。