An essential part of the transfer of knowledge in the tourism and hospitality industry, destination image is defined as the expression of objective knowledge, imagination, and the subjective emotions of the tourist. Social media is profoundly changing the way the tourist images and interacts with the destination environment. In turn, firms in the industry are seeking to leverage the power of social media to gain insights into tourist cognition and behavior. In this chapter, we analyze various social media to investigate knowledge transfer relating to two groups of hotels in Philadelphia, and we propose a methodology to predict future lodging demand from empirical data in line with the objectives of the t-Forum.

Artificial Neural Network (ANN) is an area of extensive research. The ANN has been shown to have utility in a wide range of applications. In this chapter, we demonstrate practical applications of ANN in analyzing social media data in order to gain insight into competitive analysis in the field tourism. We have leveraged the use of an ANN architecture in creating a Self-Organizing Map (SOM) to cluster all the textual conversational topics being shared through thousands of management tweets of more than ten upper class hotels in Philadelphia. By doing so, we are able not only to picture the overall strategies being practiced by those hotels, but also to indicate the differences in approaching online media among them through very lucid and informative presentations. We also carry out predictive analysis as an effort to forecast the occupancy rate of luxury and upper upscale group of hotels in Philadelphia by implementing Neural Network based time series analysis with Twitter data and Google Trend as overlay data. As a result, hotel managers can take into account which events in the life of the city will have deepest impact. In short, with the use of ANN and other complementary tools, it becomes possible for hotel and tourism managers to monitor the real-time flow of social media data in order to conduct competitive analysis over very short timeframes.

Informed use of medical tourism services depends on an up-to-date knowledge of the available services, and their costs and risks at various potential destinations. Such information can also assist in the competitive development of healthcare services. Innovation, product development, and health user relationship management by medical service providers is enhanced, as is knowledge base construction and management. This chapter shows that new forms of social media can provide valuable and previously difficult to obtain real-time knowledge on medical tourists' perceptions, concerns, and sentiment towards medical tourism destinations - both those already visited by other users and those under consideration for a possible visit. We show how analysis of comments from such social media as Twitter micro-blogs can be used to reveal potential and recent medical tourism motivations in the medical services markets in various locations.

Data, data, data. Since the advent of mass utilization of personal computers and then the Internet, digitizing of social research has provided us with what previously would have been considered an unreachable quantity of data (Dellarocas, 2003; Lagus et al., 2004). However, the fact that this data is a valuable resource has only recently been recognized. Governments, businesses, and other organizations are just beginning to learn how to turn this data into actionable information and knowledge. Traditionally, manipulation of numeric data was the main purview of analysis, most often derived from sample surveys. Now, with digitization more esoteric analysis has become available in the form of data mining of free-text for comments, attitudes, or sentiment towards objects or concepts of interest to researchers. Free or unstructured text examined through the tools of data mining has been harnessed to produce valuable knowledge that businesses, governments, and researchers can benefit from (Hepburn, 2007; Carson, 2008). For example, analyzing the free text portions of medical records shows that this information can provide new insights into patient and medical staff opinions and reactions that can assist in decision-making in the field of medical tomography (Lee, Koh & Ong, 1989). In this article we will explore this application of data mining to the study of social media and show that valuable and powerful insights generated from these media are also available in the field of tourism and hospitality (Choi et al., 2007; Ellion, 2007; Gretzel et al., 2007). The analysis of social media can provide the tourism industry with business analytic results in the short term (real-time), medium and longer term horizons (Laboy & Torchio, 2007; Jansen et al., 2009). In this, it is essentially the modern form of ‘word of mouth’, a long established and important method of finding out and influencing decisions in the tourism and hospitality industry (Dellarocas, 2003; Cooper & Eades, 2012). We investigate and describe the real-time potential, industry potential, and brand potential of the methodologies described (Mack et al., 2008; Claster et al., 2010). We also examine whether the tourism and hospitality industry can benefit from real-time monitoring of events through following social media and we investigate how the industry can make use of this knowledge advantage to allow individual businesses to outperform competitors (eMarketer, 2007; Pan et al., 2007; Pang & Lee, 2008; Akehurst, 2009). The utilization of this knowledge resource may lead to lower costs, better differentiation, more effective operational methods, and more powerful innovation in the industry (Werther & Ricci, 2004; Carson, 2005). In addition both comparative and differential advantages may be realized through the use of these methodologies. Current research indicates that social media analytics is a vital tool that must be used to innovate decision support in order to revolutionize the process landscape (Senecal & Nantel, 2004; Tajeddini et al., 2011). It is essential that real-time monitoring be incorporated in overall information strategies; businesses that fail to take advantage of this resource will fall behind and lose market share. In the same way, in addition to real-time William B. Claster Ritsumeikan Asia Pacific University, Japan

Recently social media has been shown to provide information on tourism and politics. In recent studies that we have conducted, wine sales and tourism trends have been forecast using machine learning algorithms and hundreds of thousands of blogs, online news articles and Twitter tweets. Our previous research has shown that mining of social media can predict in real-time market penetration figures and can also forecast social and business trends in tourism. We extend the research further to evaluate the predictive value of Social Media in forecasting trends for the value of publicly traded Hospitality and Tourism companies.

Tourism and hospitality organisations depend on market knowledge to compete in innovation, product development, and customer relationship management. This paper shows that new forms of social media provide valuable and previously difficult to obtain real-time knowledge on tourist perceptions, concerns, and sentiment towards tourist destinations - both those already visited and those under consideration for a future visit. We show how analysis of comments from such social media as Twitter micro-blogs can be used to reveal potential and recent tourists motivations in the travel and hospitality industry in various locations.

In this study we analyze 1024 free text digital records from pediatric patients who underwent CT scanning.The free text reports are from the digital records of patients who underwent CT scanning in a one-year period in 2004 at the Nagasaki University Medical Hospital in Japan.We use text mining algorithms to model the records.Each scan was evaluated by an expert in the field and classified as to whether the CT scan was necessary or not.A model was built that predicts this classification.The results show that models developed on raw text could contribute significantly to the physician's decision to order a CT scan.Practically this is important because radiation at levels ordinarily used for CT scanning may pose significant health risks especially to children and thus the modeling of unnecessary scanning may lead to less exposure to radiation.

In this paper we mine over 80 million twitter microblogs in order to explore whether data from the social media initiative known as Twitter can be used to identify sentiment about red wines. We test to see whether models derived from Twitter data can corroborate industry sales figures and we employ text analysis software developed to assess emotional, cognitive, and structural components of text to analyze the twitter dataset to harvest knowledge about consumer sentiment on different wine varietals. A multi-knowledge based approach is proposed using, Self-Organizing Maps and domain expertise in order to establish view the social network conversation. We show that it is possible to both confirm previously known knowledge and find novel information through the proposed methodology.

Some common methodologies in our everyday life are not based on modern scientific knowledge but rather a set of experiences that have established themselves through years of practice. As a good example, there are many forms of alternative medicine, quite popular, however difficult to comprehend by conventional western medicine. The diagnostic and therapeutic methodologies are very different and sometimes unique, compared to that of western medicine. How can we verify and analyze such methodologies through modern scientific methods? We present a case study where data-mining was able to fill this gap and provide us with many tools for investigation. Osteopathy is a popular alternative medicine methodology to treat musculoskeletal complaints in Japan. Using data-mining methodologies, we could overcome some of the analytical problems in an investigation. We studied diagnostic records from a very popular osteopathy clinic in Osaka, Japan that included over 30,000 patient visits over 6 years of practice. The data consists of some careful measurements of tissue electro-conductivity differences at 5 anatomical positions. Data mining and knowledge discovery algorithms were applied to search for meaningful associations within the patient data elements recorded. This study helped us scientifically investigate the diagnostic methodology adopted by the osteopath.

Sentiment mining aims at extracting features on which users express their opinions in order to determine the user’s sentiment towards the query object. Movie sentiment in Twitter provides an excellent base upon which to evaluate sentiment mining methodologies both because of the pervasiveness of discussions devoted to movie topics and because of the brevity of expression induced by twitter's 140 word limitation. In this paper we explore movie sentiment expressed in Twitter microblogs. A multi-knowledge based approach is proposed using, Self-Organizing Maps and movie knowledge in order to model opinion across a multi-dimensional sentiment space. We develop a visual model to express this taxonomy of sentiment vocabulary and then apply this model in test data. The results show the effectiveness of the proposed visualization in mining sentiment in the domain of Twitter tweets.

Sentiment mining aims at extracting features on which users express their opinions in order to determine the user's sentiment towards the query object. We mine over 70 million Twitter microblogs to gain knowledge regarding tourist sentiment on the travel resort destination Cancun in the Yucatan Peninsula of Mexico. We measure sentiment using a binary choice keyword algorithm and a multi-knowledge based approach is proposed using, Self-Organizing Maps and tourism domain knowledge in order to model sentiment. We develop a visual model to express this taxonomy of sentiment vocabulary and then apply this model to maximums and minimums in the time sentiment data. The results show practical knowledge can be extracted.

There is a treasure trove of hidden information in the textual and narrative data of medical records that can be deciphered by text-mining techniques. The information provided by these methods can provide a basis for medical artificial intelligence and help support or improve clinical decision making by medical doctors. In this paper we extend previous work in an effort to extract meaningful information from free text medical records. We discuss a methodology for the analysis of medical records using some statistical analysis and the Kohonen Self-Organizing Map (SOM). The medical data derive from about 700 pediatric patients’ radiology department records where CT (Computed Tomography) scanning was used as part of a diagnostic exploration. The patients underwent CT scanning (single and multiple) throughout a one-year period in 2004 at the Nagasaki University Medical Hospital. Our approach led to a model based on SOM clusters and statistical analysis which may suggest a strategy for limiting CT scan requests. This is important because radiation at levels ordinarily used for CT scanning may pose significant health risks especially to children.

In this paper we mine over 80 million twitter micro logs in order to explore whether data from this social media initiative can be used to identify sentiment about tourism and Thailand amid the unrest in that country during the early part of 2010 and further whether analysis of tweets can be used to discern the effect of that unrest on Phuket's tourism environment. It is proposed that this analysis can provide measurable insights through summarization, keyword analysis and clustering. We measure sentiment using a binary choice keyword algorithm. A multi-knowledge based approach is proposed using, Self-Organizing Maps along with sentiment polarity in order to model sentiment. We develop a visual model to express a sentiment concept vocabulary and then apply this model to maximums and minimums in the time series sentiment data. The results show actionable knowledge can be extracted in real time.

This paper proposes an alternate view for understanding clusters and for determination of the variables that play a significant role in cluster makeup. We explore the creation of a new categorical variable from a given set of variables by means of the output of a clustering algorithm. We postulate that this new variable can be seen as being comprised of a few “important” variables and explore how this new variable relates to the original variables. Sensitivity analysis and discriminant analysis are used to confirm the selection of important variables. Then we show that this method is able to identify those key variables which vary most significantly throughout the clusters.

In recent years, information and communication technology and multimedia technology have increasingly altered the landscape of the educational field particularly in higher education. In that, e-learning in its broad sense makes use of network and computing resources for bringing general education to the potential benefits of distant education and face to face classroom education. The amount of multimedia support facilitated by the e-learning systems has given significant consideration in order to make distance education as effective as classroom education and make the blended leaning experience more effective. While the technology is moving toward a multimedia rich learning management system, its practical deployments is still far away, due to many unsolved technical and pedagogical problems. In this paper we discuss the design and implementation of a prototype system umeLMS which features an integrated framework that interacts with a rich set of hypermedia contents and provides ubiquitous access. The main focus of this design is threefold: first input integration by which multimedia can be incorporated into the LMS in various ways. Second, content Integration by which different forms of hypermedia is linked to the course contents. Third, access integration by which a wide array of mobile devices are supported for multimedia content browsing which creates a real u-learning environment by enabling active participation in the learning/teaching process.

Osteopathy is a relatively common form of alternative medicine modalities used to treat musculoskeletal complaints in Japan. However, the diagnostic and therapeutic manipulations used are very different and sometimes unique, compared to that of western medicine. One problem is the difficulties in verification of alternative medical practices through modern clinical scientific methods. We examined whether and how data-mining methodologies can be applied to overcome some of the problems. We were fortunate to obtain diagnostic records from a very popular osteopathy clinic in Osaka, Japan thatincluded over 30,000 patient visits over 6 years of practice. The data consists of some careful measurements of tissue electro-conductivity differences at 5 anatomical positions which as a whole are looked upon as an indication of the most appropriate approach/ location of the patient's problem. These include the left and right side of the neck, the armpits, the wrists, the knees, and the ankles. Our research group received these records and applied data mining and knowledge discovery algorithms to look for any scientifically meaningful associations within the patient data elements recorded. This study might assist the osteopath in discovering potentially useful and valuable knowledge in the form of patterns/correlations within the data elements and more importantly to help us scientifically verify the diagnostic methodology adopted by the osteopath.

The rapid growth of digitalized medical records presents new opportunities for mining terra bytes of data that may provide new information & knowledge. The knowledge discovered as such could assist medical practitioners in a myriad of ways, for example in selecting the optimal diagnostic tool from among numerous possible choices. We analyzed the radiology department records of children who had undergone a CT scan procedure at Nagasaki University Hospital in the year 2004. We employed Self Organizing Maps (SOM), an unsupervised neural network based text-mining technique for the analysis. This approach led to the identification of keywords with a significance value within the narratives of the medical records that could predict & thereby lower the number of unnecessary CT requests by clinicians. This is important because, in spite of the valuable diagnostic capacity of such procedures, the overuse of medical radiation does pose significant health risks and staggering cost especially with regard to children.