AMuse – An Initial Plan to Associate Museum Visits to Outdoor Cultural Heritage Activities Alan J. Wecker Tsvi Kuflik Oliviero Stock U. of Haifa, U of Trento University of Haifa FBK Haifa, Israel - Trento, Italy Haifa, Israel Trento, Italy ajwecker@gmail.com tsvikak@is.haifa.ac.il stock@fbk.edu ABSTRACT inform us in the cultural heritage field with the proper . In this paper, we examine a possible plan to associate adaptations. For example from Ardicvilli et al. [3] we use: museum visits with outdoor cultural heritage activities. The "while elements of opportunities may be "recognized", plan consists of looking at museum visit movement styles opportunities are made, not found" and "therefore [prefer] to predict personality and learning styles, and using holding opportunity development rather than opportunity power to determine user interests. We then describe how recognition". They define opportunity as the chance to meet this information can be utilized to both suggest possible a market need (or interest or want) through a creative venues (opportunity development) and provide associated combination of resources to deliver superior value. In content (opportunity exploitation) at opportune location and addition the field of opportunity identification as related to times in novel ways. cultural heritage has been studied under tourism research [1, 11], however not in the mobile context and not in the Author Keywords context of personalization and connection to prior museum Lifelong Cultural Heritage; Mobile Museum Guides; experiences. Verbke and Rekom [11] discuss the concept Opportunity Identification; Opportunity Exploitation of the "museumpark" of multiple museums having a ACM Classification Keywords positive marketing effect. One could postulate that the H.5.m. Information interfaces and presentation (e.g., HCI): indoor-outdoor connection may also have a similar effect. Miscellaneous. Motivations (24 items) and incentives for cultural heritage are clearly part of the opportunity identification and are INTRODUCTION listed by [11]. A number of meta-issues have begun to emerge in the use In order to do opportunity identification, we need to of technology for cultural heritage. Among these meta- understand additional motivations and incentives present in issues is "lifelong cultural heritage"[13]. This entails many the cultural heritage field. Amy Jones [20] discusses the different aspects. One aspect is connecting museum visits motivational factors for success in the mobile learning to other cultural heritage visits. Another trend is the context: We believe that these items are relevant for the emergence of commercial systems, such as Google Field mobile cultural heritage experience that we aim to Trip[https://www.fieldtripper.com/#], TourML standard construct, and should be adapted as motivational factors for app[22], that provide information on more than one venue. this experience (See Table 1). This paper presents significant progress and details on the work described in [23]. In addition we use principles Motivational Factor Relevancy to Cultural Heritage described in [15]. Control Pro-activeness [16] BACKGROUND Ownership Connection, Identity [7] Part of the work is based on marketing theory of opportunity identification and exploitation. Opportunity Fun Quality of Experience [18] identification is a theme that has been intensively studied Communication Social Aspects [19] for business purposes [3, 6, 8, 9] and can possibly serve to Learning in context Free Choice Learning [7] Copyright held by authors . Continuity between Coherency [5, 24] contexts Table 1. Motivational Factors Visitors have been observed to behave in certain stereotypical movement patterns [25]; patterns such as Butterfly, Grasshopper Ant, and Fish, [21]. We extend this concept of movement patterns to include usage patterns of mobile guides. The use of personality types to tailor software is not new. addition we can use the visitor's choice of media assets to We use the SLOAN Big 5 characterization as it is standard determine user media preferences. At the end of the visit and much research has been done using it [10]. We focus the user is asked to download an application to their on two traits we believe are connected to the museum smartphone and register thereby connecting their visit experience: Inquisitiveness which is a measure of curiosity information to future opportunities. and Orderliness which measures thoroughness and the need for structure. Introversion and Extroversion could also play Computing Personal Charecteristics a part in group visits, but is not examined in this research. In order to characterize the user we make use of his general In addition we posit a connection between movement types movement activities. We use the following statistics: and "identity" types proposed by John Falk [7]. In addition, x NumberOfPOIsVisted (NPV) – This is the number preliminary ideas for the connection of movement patterns of positions where a person stayed more than 9 to personality types have been proposed [2]. seconds as detected and logged by the mobile guide's positioning system. Nine seconds is a SYSTEM DESCRIPTION The system AMuse (Associating MUSEums) is being number we have used for previous analysis and developed to bridge a perceived gap between the museum has provided good results experience and subsequent experiences at cultural heritage x POIsWherePresentationsSeen (PPS) – This is the sites as part of the effort to develop lifelong cultural number of positions where the visitor viewed at heritage [14]. In order to provide a framework for this least one media asset connected to that position as experience we adopt parts of "opportunity" theory from computed from the logs of the mobile guide. marketing research.. The system operates in three venues: the museum, pre-visit, close by an external site. x NumberOfPresentationSeen (NPS) – This is the total number of media assets the visitor viewed as x The system attempts to learn about the user computed from the logs of the mobile guide. through his movement and use of mobile guide in the museum (Information Gathering) Type Formula x The system develops opportunities to give (NPV – PPS >= PPS) || personal advice at appropriate times advice where Fish ((PPS/NPV < = T1) & is it worth visiting given the above. This is in-line with marketing theory which suggests that (NPS/PPS < T3 )) opportunities don't just present themselves but are (PPS/NPV > T1 ) & nurtured. (Opportunity development). Ant (NPS/PPS > T2) x When an immediate opportunity (primarily a (PPS/NPV > T1) & location, but can be a date, news item, or person) Butterfly presents itself, an appropriate associated media (NPS/PPS < T2) asset is presented to the user. (Opportunity (PPS/NPV < T1) & exploitation). Grasshopper (NPS/PPS > T3) Information Gathering Table 2. Classification of users based on movement The system assumes the use of a mobile guide, which is associated with points of interest (POI). The mobile guide, The thresholds T1=0.5, T2=0.5, T3=0.3 were obtained by at each POI, presents a list of relevant media assets. The experimental trial and error until a good clustering was mobile guide system logs: the POI, which assets are chosen obtained on visitor data at the Hecht Museum (n=400). how long they viewed the asset, and in general how long If we take the meaning of the formulas what we are positing did they stay at the point of interest. The logs are converted is that a fish sees very little presentations but wanders into a proposed standard format, consisting of events and around. An ant visits a large number of POIs and sees a activities to be later processed by the system. This data is be large number of media assets at each spot they visit; while a augmented by identity and demographic information butterfly also sees a large number of POIs, they sees less collected explicitly either at the time of registration or at the media assets. A grasshopper visits few POIs but sees end of the visit. We collect two types of information, the relatively many media assets. first in order to determine general personal characteristics and the second in order to determine specific topic interests. Computing Visitor Interest Preferences In general we use movement styles, such as ant, Using standard methodology each POI has associated with grasshopper, butterfly, and fish to predict user it a number of tags taken from a specific ontology (possibly characteristics (such as personality). We use time viewing with weights). In addition each media asset has associated presentations in order to determine user topic interests. In with it a number of tags taken from a specific ontology (again possibly with weights). Using the logs of the guide factors such as location, time, and weather, rank them, we determine time spent (either at the POI or with a media present them to the user and try to motivate the user to asset). These durations are normalized and added to the user commit to visiting one of the sites (for example, adding the model. visit to his calendar or using a planning application for the intended site). Again not as a specific recommendation but Other Information Garnered using the site information embedded in more subtle If the guide has a variety of media types to choose from, message then the system can ascertain which media format the user prefers by looking at the museum mobile guide logs to Personality types can affect the frequency of determine what are their preferred media format (audio, communication, marketing strategy (direct, indirect, door in video, pictures) and add this information to the user model. the face vs. foot in the door) and length of message. For example an ant's message may contain many Additionally we can explicitly ask on which day of the recommendations of places to visit; while a grasshopper week the user plans their weekend leisure activities. We may have a focused list of only 1 or 2 items. may also ask their preferred communication channel (e- mail, SMS, smartphone notification, voice message) In addition each communication can begin or end with one of the following incentive messages. Incentives are: be If the visitor takes pictures, using the guide, or provides given food for thought, not stand still in life, quality of life, access to his tagged photos, these may also be used by the enrich your life, learn something, watch works of art, visit a system. If the user grants access to their social network, museum and seeing something new. The incentives chosen then this information may also be used to provide content. are matched to the personality types. Making Inferences from Movement Styles Opportunity Exploitation As discussed above we make inferences from the Depending on location, (primarily but also significant dates movement styles to two of the Big Five personality traits, and the availability of news items), when they are near a inquisitiveness (I) & non-inquisitive (N), and orderliness site they gets a notification that there is information (O) & unorderly (U), which are also referred to as connecting them to a previous museum visit. The temperament. An additional inference can also be made to presentations consist of an introduction (given once), a the Falk type. We also list their percentage in the reminder of how this is connected to the museum. At the population [21] end they will get a summary message. Frequency and amount of notification, content depends on interests and Movement Curiosity Attention Big 5 Falk type % personality characteristics. The content is focused less on pattern Span providing content concerning the current site (which may be provided by a local mobile guide) but rather on content which connects the user to previous cultural heritage Grasshopper Low High NO Professional 41 experiences. This material can be information, visual or Hobbyist text which has a connection to the present opportunity. In addition we try to take advantage of social information such Fish Low Low NU Recharger 33 as picture of friends or family at the site. There is an importance of coherency and duplication avoidance, that we Ant High High IO Explorer 10 try to maintain when providing information. Butterfly High Low IU Experience 16 EVALUATION AND DISCUSSION Seeker As the system is in its initial stages at present and only ad- hoc evaluation is available .The need for such a system was evaluated with a questionnaire and showed positive results. Table 3 Movement to Personality In addition the definition of the thresholds and formulas Opportunity Development where tested on real visitor data to see if it provided Using the information gathered above, the system prepares adequate clustering. Of course other formulas for the itself to develop opportunities that can be later exploited. movement types can be used, but these formulas seem to be As in marketing advertisements there is an emphasis on the a reasonable start. subtle approach and gentle persuasion. CONCLUSIONS We attempt to accomplish this by using the user's interests Some of the innovative aspects of the system include: Use to search a database for possible venues to visit[4, 12, 17]. of observed user behavior in museum to build up model; Initially we try only to make the user aware of possible System responsible for managing long-term process sites given his communication preference. After this initial (awareness, motivation, commitment); Use of social message we filter these possibilities using contextual information for cultural heritage content (not just reflection); Taking into account the users context (device weather, when delivering content and recommendations) (bandwidth, display size, audio capabilities), time of day, REFERENCES [13] Kuflik, T., Kay, J. and Kummerfeld, B. Lifelong Personalized Museum Experiences. Proc.Pervasive User [1] Alzua, A., O'Leary, J. T. and Morrison, A. Cultural and Modeling and Personalization (PUMP'10), ( 2010). heritage tourism: identifying niches for international travellers. Journal of Tourism Studies, 9, 2 ( 1998), 2-13. [14] Kuflik, T., Kay, J. and Kummerfeld, B. Lifelong personalized museum experiences. In Anonymous [2] Antoniou, A., Lepouras, G., Lykourentzou, I. and Proceedings of Workshop on Pervasive User Modeling and Naudet, Y. Connecting physical space, human personalities Personalization (PUMP’10). (). , 2010, 9-16. and social networks. (). [15] Kuflik, T., Wecker, A. J., Lanir, J. and Stock, O. An [3] Ardichvili, A., Cardozo, R. and Ray, S. A theory of integrative framework for extending the boundaries of the entrepreneurial opportunity identification and development. museum visit experience: linking the pre, during and post Journal of Business Venturing, 18, 1 ( 2003), 105-123. visit phases. Information Technology & Tourism, ( 2014), [4] Ardissono, L., Kuflik, T. and Petrelli, D. Personalization 1-31. in cultural heritage: the road travelled and the one ahead. [16] Lanir, J., Kuflik, T., Wecker, A. J., Stock, O. and User Modeling and User-Adapted Interaction, 22, 1 ( 2011), Zancanaro, M. Examining proactiveness and choice in a 1-27. location-aware mobile museum guide. Interact Comput, ( [5] Callaway, C., Stock, O., Dekoven, E., Noy, K., Citron, 2011). Y. and Dobrin, Y. Mobile drama in an instrumented [17] Pu, P., Chen, L. and Hu, R. Evaluating recommender museum: inducing group conversation via coordinated systems from the user’s perspective: survey of the state of narratives. In Anonymous Proceedings of the 16th the art. User Modeling and User-Adapted Interaction, 22, 4- international conference on Intelligent user interfaces. 5 ( 2012), 317-355. (Palo Alto, California, USA, ). ACM, , 2011, 73-82. [18] Shneiderman, B. and Plaisant, C. Designing the user [6] Corbett, A. C. Experiential learning within the process interface. Addison-Wesley Reading, MA, , 2009. of opportunity identification and exploitation. Entrepreneurship Theory and Practice, 29, 4 ( 2005), 473- [19] Szymanski, M. H., Aoki, P. M., Grinter, R. E., Hurst, 491. A., Thornton, J. D. and Woodruff, A. Sotto Voce: Facilitating Social Learning in a Historic House. Computer [7] Falk, J. H. Identity and the museum visitor experience. Supported Cooperative Work (CSCW), 17, 1 ( 2008), 5-34. Left Coast Press Walnut Creek, CA, , 2009. [20] Traxler, J. Learning in a mobile age. International [8] Gaglio, C. M. The Role of Mental Simulations and Journal of Mobile and Blended Learning (IJMBL), 1, 1 ( Counterfactual Thinking in the Opportunity Identification 2009), 1-12. Process*. Entrepreneurship Theory and Practice, 28, 6 ( 2004), 533-552. [21] Veron, E. and Levasseur, M. Ethnographie de l'exposition. Centre Georges Pompidou, , 1983. [9] Gaglio, C. M. and Katz, J. A. The psychological basis of opportunity identification: Entrepreneurial alertness. Small [22] Watson, R., Akselsen, S., Monod, E. and Pitt, L. The Business Economics, 16, 2 ( 2001), 95-111. Open Tourism Consortium::: Laying The Foundations for the Future of Tourism. European Management Journal, 22, [10] Higgins, D. M., Peterson, J. B., Pihl, R. O. and Lee, A. 3 ( 2004), 315-326. G. Prefrontal cognitive ability, intelligence, Big Five personality, and the prediction of advanced academic and [23] Wecker, A. J., Kuflik, T. and Stock, O. Personalized workplace performance. J. Pers. Soc. Psychol., 93, 2 ( Cultural Heritage Experience outside the Museum 2007), 298. Connecting the outside world to the museum experience. ( 2013). [11] Jansen-Verbeke, M. and Van Rekom, J. Scanning museum visitors: Urban tourism marketing. Ann. Tourism [24] Wolff, A., Mulholland, P. and Collins, T. Modelling Res., 23, 2 ( 1996), 364-375. the Meaning of Museum Stories. In Anonymous (Portlan, Oregon, ). , 2013. [12] Konstan, J. A. and Riedl, J. Recommender systems: from algorithms to user experience. User Modeling and [25] Zancanaro, M., Kuflik, T., Boger, Z., Goren-Bar, D. User-Adapted Interaction, 22, 1-2 ( 2012), 101-123. and Goldwasser, D. Analyzing museum visitors’ behavior patterns. User Modeling 2007, ( 2007), 238-246.