scholarly journals Aggregating social media data with temporal and environmental context for recommendation in a mobile tour guide system

2016 ◽  
Vol 7 (3) ◽  
pp. 281-299 ◽  
Author(s):  
Kevin Meehan ◽  
Tom Lunney ◽  
Kevin Curran ◽  
Aiden McCaughey
Keyword(s):  
Social Media ◽  
Recommender System ◽  
Real World ◽  
Environmental Context ◽  
User Preferences ◽  
Temporal Context ◽  
Tour Guide ◽  
Social Media Data ◽  
Content Type ◽  
Media Data

Purpose Manufacturers of smartphone devices are increasingly utilising a diverse range of sensors. This innovation has enabled developers to accurately determine a user’s current context. One area that has been significantly enhanced by the increased use of context in mobile applications is tourism. Traditionally, tour guide applications rely heavily on location and essentially ignore other types of context. This has led to problems of inappropriate suggestions and tourists experiencing information overload. These problems can be mitigated if appropriate personalisation and content filtering is performed. This research proposes an intelligent context-aware recommender system that aims to minimise the highlighted problems. Design/methodology/approach Intelligent reasoning was performed to determine the weight or importance of different types of environmental and temporal context. Environmental context such as the weather outside can have an impact on the suitability of tourist attractions. Temporal context can be the time of day or season; this is particularly important in tourism as it is largely a seasonal activity. Social context such as social media can potentially provide an indication of the “mood” of an attraction. These types of contexts are combined with location data and the context of the user to provide a more effective recommendation to tourists. The evaluation of the system is a user study that utilised both qualitative and quantitative methods, involving 40 participants of differing gender, age group, number of children and marital status. Findings This study revealed that the participants selected the context-based recommendation at a significantly higher level than either location-based recommendation or random recommendation. It was clear from analysing the questionnaire results that location is not the only influencing factor when deciding on a tourist attraction to visit. Research limitations/implications To effectively determine the success of the recommender system, various combinations of contextual conditions were simulated. Simulating contexts provided the ability to randomly assign different contextual conditions to ensure an effective recommendation under all circumstances. This is not a reflection of the “real world”, because in a “real world” field study the majority of the contextual conditions will be similar. For example, if a tourist visited numerous attractions in one day, then it is likely that the weather conditions would be the same for the majority of the day, especially in the summer season. Practical implications Utilising this type of recommender system would allow the tourists to “go their own way” rather than following a prescribed route. By using this system, tourists can co-create their own experience using both social media and mobile technology. This increases the need to retain user preferences and have it available for multiple destinations. The application will be able to learn further through multiple trips, and as a result, the personalisation aspect will be incrementally refined over time. This extensible aspect is increasingly important as personalisation is gradually more effective as more data is collated. Originality/value This paper contributes to the body of knowledge that currently exists regarding the study of utilising contextual conditions in mobile recommender systems. The novelty of the system proposed by this research is the combination of various types of temporal, environmental and personal context data to inform a recommendation in an extensible tourism application. Also, performing sentiment analysis on social media data has not previously been integrated into a tourist recommender system. The evaluation concludes that this research provides clear evidence for the benefits of combining social media data with environmental and temporal context to provide an effective recommendation.

scholarly journals Social Media Data Analysis using Recommendation Algorithms

2019 ◽  
Vol 8 (12S) ◽  
pp. 394-397
Keyword(s):  
Social Media ◽  
Data Analysis ◽  
Recommender System ◽  
User Preferences ◽  
Implicit Feedback ◽  
Social Media Data ◽  
Recommendation Algorithms ◽  
The Subject ◽  
Media Data ◽  
Explicit Feedback

Recommender frameworks (RSs) are utilized in application areas to help clients in the quest for their preferred items .Recommender system filters information which takes users ratings and predict user preferences in ecommerce and other categorical websites. We examine individual proposal dependent on client inclinations and search the neighbors through the client inclinations. It generates recommendations based on implicit feedback or explicit feedback. Implicit feedback is based on analysis of browsing patterns of the user. Express criticism is produced from the appraisals given by the client. All the more extensively tended to was the subject of AI's calculations, centered around separating calculations dependent on the clients or questions, and dependent on substance.

scholarly journals Communication Sentiment Analyzer using Machine Learning with Naive Bayes Bernoullinb

2019 ◽  
Vol 9 (1) ◽  
pp. 5976-5979
Keyword(s):  
Machine Learning ◽  
Social Media ◽  
Major Part ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
User Preferences ◽  
Social Media Data ◽  
Machine Learning Model ◽  
The World ◽  
Media Data

In this never-ending social media era it is estimated that over 5 billion people use smartphones. Out of these, there are over 1.5 billion active users in the world. In which we all are a major part and before opening our messages we all are curious about what message we have received. No doubt, we all always hope for a good message to be received. So Sentiment analysis on social media data has been seen by many as an effective tool to monitor user preferences and inclination. Finally, we propose a scalable machine learning model to analyze the polarity of a communicative text using Naive Bayes’ Bernoulli classifier. This paper works on only two polarities that is whether the sentence is positive or negative. Bernoulli classifier is used in this paper because it is best suited for binary inputs which in turn enhances the accuracy of up to 97%.

Destination image through social media analytics and survey method

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Michael S. Lin ◽  
Yun Liang ◽  
Joanne X. Xue ◽  
Bing Pan ◽  
Ashley Schroeder
Keyword(s):  
Social Media ◽  
Survey Data ◽  
Destination Image ◽  
Social Media Analytics ◽  
Tourism Destination ◽  
Social Media Data ◽  
Content Type ◽  
Holistic Understanding ◽  
Intercept Survey ◽  
Media Data

Purpose Recent tourism research has adopted social media analytics (SMA) to examine tourism destination image (TDI) and gain timely insights for marketing purposes. Comparing the methodologies of SMA and intercept surveys would provide a more in-depth understanding of both methodologies and a more holistic understanding of TDI than each method on their own. This study aims to investigate the unique merits and biases of SMA and a traditional visitor intercept survey. Design/methodology/approach This study collected and compared data for the same tourism destination from two sources: responses from a visitor intercept survey (n = 1,336) and Flickr social media photos and metadata (n = 11,775). Content analysis, machine learning and text analysis techniques were used to analyze and compare the destination image represented from both methods. Findings The results indicated that the survey data and social media data shared major similarities in the identified key image phrases. Social media data revealed more diverse and more specific aspects of the destination, whereas survey data provided more insights in specific local landmarks. Survey data also included additional subjective judgment and attachment towards the destination. Together, the data suggested that social media data should serve as an additional and complementary source of information to traditional survey data. Originality/value This study fills a research gap by comparing two methodologies in obtaining TDI: SMA and a traditional visitor intercept survey. Furthermore, within SMA, photo and metadata are compared to offer additional awareness of social media data’s underlying complexity. The results showed the limitations of text-based image questions in surveys. The findings provide meaningful insights for tourism marketers by having a more holistic understanding of TDI through multiple data sources.

Using social media data in diabetes care: Bridging the conceptual gap between health providers and patients (Preprint)

2021 ◽  
Author(s):  
Ru-Hsueh Wang ◽  
Yu-Wen Hong ◽  
Chia-Chun Li ◽  
Siao-Ling Li ◽  
Jenn-Long Liu ◽  
...  
Keyword(s):  
Social Media ◽  
Chinese Medicine ◽  
Sexual Dysfunction ◽  
Text Mining ◽  
Real World ◽  
Diabetes Care ◽  
Weight Reduction ◽  
Health Providers ◽  
Social Media Data ◽  
Media Data

BACKGROUND Diabetic patients with poor education about the disease may exhibit poor compliance and thus subsequently experience more complications. However, the conceptual gap between the diabetes education provided by health providers and the non-compliance of patients is still not well understood in the real world. OBJECTIVE Disclosing what people think about diabetes on social media may help to close this gap. METHODS In this study, social media data was collected from the OpView social media platform. After checking the quality of the data, we analyzed the trends in people’s discussions on the Internet using text mining. The natural language process, including word segmentation, and word count, and counting the relationships between the words. A word cloud is developed, and a clustering analyses are also performed. RESULTS There were 19,565 posts about diabetes collected from forums, community websites, and Q&A websites in 2017. The three most popular aspects of diabetes were diet (33.2%), life adjustment (21.2%), and avoiding complications (15.6%). Most of the discussions about diabetes were negative, and the top three negative ratios aspects were avoiding complications (7.60), problem-solving (4.08) and exercise (3.97). In terms of diet, the most popular topics were Chinese medicine and special diet therapy. In terms of life adjustment, financial issues, weight reduction, and a less painful glucometer were discussed the most. Furthermore, sexual dysfunction, neuropathy, nephropathy, and retinopathy were the most worrying issues in the avoiding complications area. Using text mining, we found that people care most about sexual dysfunction. Health providers care about the benefits of exercise in diabetes care, but people are mostly really concerned about sexual functioning. CONCLUSIONS A conceptual gap between health providers and diabetes patients existed in this real-world social media investigation. To spread healthy diabetic education concepts in the media, health providers might wish to provide more information related to patients actual areas of concern, such as sexual function, Chinese medicine, and weight reduction.

Determining factors of participants' attitudes toward the ethics of social media data research

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Yi Chen ◽  
Chuanfu Chen ◽  
Si Li
Keyword(s):  
Social Media ◽  
Structural Equation ◽  
Ethical Issues ◽  
Equation Modeling ◽  
Research Subjects ◽  
Social Media Data ◽  
Content Type ◽  
Mediating Role ◽  
Determining Factors ◽  
Media Data

PurposeThe purpose of this study was to investigate the participants' attitudes toward the ethical issues caused by collecting social media data (SMD) for research, as well as the effects of familiarity, trust and altruism on the participants' attitudes toward the ethics of SMD research. It is hoped that through this study, scholars will be reminded to respect participants and engage in ethical reflection when using SMD in research.Design/methodology/approachThis study adopted social media users as its research subjects and used Sina Microblog, the world's largest Chinese social media platform, as the example. Based on the 320 valid responses collected from a survey, structural equation modeling was employed to examine the research model.FindingsThe results indicated that altruism, familiarity and trust have significant influences on participants' attitudes toward the ethics of SMD research, and familiarity also influences attitudes through the mediating role of trust and altruism.Originality/valueThis study explored the mechanism underlying the relationship between the determining factors and participants' attitudes toward the ethics of SMD research, and the results demonstrated that the informed consent mechanism is an effective way to communicate with participants and that the guiding responsibility of the platform should be improved to standardize SMD research.

Forecasting daily attraction demand using big data from search engines and social media

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Fengjun Tian ◽  
Yang Yang ◽  
Zhenxing Mao ◽  
Wenyue Tang
Keyword(s):  
Social Media ◽  
Big Data ◽  
Search Engine ◽  
Elastic Net ◽  
Percentage Error ◽  
Mean Square ◽  
Social Media Data ◽  
Content Type ◽  
Forecasting Error ◽  
Media Data

Purpose This paper aims to compare the forecasting performance of different models with and without big data predictors from search engines and social media. Design/methodology/approach Using daily tourist arrival data to Mount Longhu, China in 2018 and 2019, the authors estimated ARMA, ARMAX, Markov-switching auto-regression (MSAR), lasso model, elastic net model and post-lasso and post-elastic net models to conduct one- to seven-days-ahead forecasting. Search engine data and social media data from WeChat, Douyin and Weibo were incorporated to improve forecasting accuracy. Findings Results show that search engine data can substantially reduce forecasting error, whereas social media data has very limited value. Compared to the ARMAX/MSAR model without big data predictors, the corresponding post-lasso model reduced forecasting error by 39.29% based on mean square percentage error, 33.95% based on root mean square percentage error, 46.96% based on root mean squared error and 45.67% based on mean absolute scaled error. Practical implications Results highlight the importance of incorporating big data predictors into daily demand forecasting for tourism attractions. Originality/value This study represents a pioneering attempt to apply the regularized regression (e.g. lasso model and elastic net) in tourism forecasting and to explore various daily big data indicators across platforms as predictors.

scholarly journals Tackling social media data analysis

2019 ◽  
Vol 22 (2) ◽  
pp. 94-113 ◽  
Author(s):  
Violetta Wilk ◽  
Geoffrey N. Soutar ◽  
Paul Harrigan
Keyword(s):  
Social Media ◽  
Data Analysis ◽  
Exploratory Research ◽  
Online Data ◽  
Social Media Data ◽  
Content Type ◽  
Advantages And Disadvantages ◽  
Brand Advocacy ◽  
Qualitative Data Analysis Software ◽  
Media Data

PurposeThis paper aims to offer insights into the ways two computer-aided qualitative data analysis software (CAQDAS) applications (QSR NVivo and Leximancer) can be used to analyze big, text-based, online data taken from consumer-to-consumer (C2C) social media communication.Design/methodology/approachThis study used QSR NVivo and Leximancer, to explore 200 discussion threads containing 1,796 posts from forums on an online open community and an online brand community that involved online brand advocacy (OBA). The functionality, in particular, the strengths and weaknesses of both programs are discussed. Examples of the types of analyses each program can undertake and the visual output available are also presented.FindingsThis research found that, while both programs had strengths and weaknesses when working with big, text-based, online data, they complemented each other. Each contributed a different visual and evidence-based perspective; providing a more comprehensive and insightful view of the characteristics unique to OBA.Research limitations/implicationsQualitative market researchers are offered insights into the advantages and disadvantages of using two different software packages for research projects involving big social media data. The “visual-first” analysis, obtained from both programs can help researchers make sense of such data, particularly in exploratory research.Practical implicationsThe paper provides practical recommendations for analysts considering which programs to use when exploring big, text-based, online data.Originality/valueThis paper answered a call to action for further research and demonstration of analytical programs of big, online data from social media C2C communication and makes strong suggestions about the need to examine such data in a number of ways.

scholarly journals The UK private housebuilding sector: social media perspectives

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Nigel Craig ◽  
Nick Pilcher ◽  
Rebecca MacKenzie ◽  
Chris Boothman
Keyword(s):  
Social Media ◽  
Customer Service ◽  
Social Media Data ◽  
Negative Image ◽  
Content Type ◽  
Safety Standards ◽  
The Uk ◽  
House Building ◽  
Media Data ◽  
Media Forum

Purpose The UK private housebuilding sector is the key supplier of new-build homes for customers, constituting a fifth of the entire UK construction industry. Yet, despite the high average cost of houses, and official reports advocating improvement, the sector remains blighted by criticism and a negative image of its quality. However, social media now offers customers new sources of advice and information. In this context, the purpose of this paper is to analyse social media forum posts from new-build homebuyers to reveal perceptions of the industry and illustrate the value of such data for others. Design/methodology/approach This paper presents and thematically analyses 147 comment posts from nine online Facebook forums under the themes of safety; standards; quality; workmanship; customer service; finance and money; advice; National House Building Council; ombudsman; and page closures. Findings Customers express frustration, anger, feelings of neglect and of an abdication of responsibility by the sector. Fundamentally, change is suggested at a systemic level, and it is urged this occurs through powerful and independent bodies. Originality/value To date, social media data has not been analysed in the context of the housebuilding sector. Yet, such data is key not only for its open and wide-reaching nature but also because it can be incorporated into government reports. It is hoped such data will be used by the new home ombudsman the UK Government hopes to establish in 2020 and help rectify many of the performance issues experienced and protect homebuyers.

Automated Discovery of Lead Users and Latent Product Features by Mining Large Scale Social Media Networks

2015 ◽  
Vol 137 (7) ◽  
Author(s):  
Suppawong Tuarob ◽  
Conrad S. Tucker
Keyword(s):  
Social Media ◽  
Large Scale ◽  
User Preferences ◽  
Social Media Data ◽  
Social Media Networks ◽  
Lead User ◽  
Product Features ◽  
Latent Features ◽  
Lead Users ◽  
Media Data

Lead users play a vital role in next generation product development, as they help designers discover relevant product feature preferences months or even years before they are desired by the general customer base. Existing design methodologies proposed to extract lead user preferences are typically constrained by temporal, geographic, size, and heterogeneity limitations. To mitigate these challenges, the authors of this work propose a set of mathematical models that mine social media networks for lead users and the product features that they express relating to specific products. The authors hypothesize that: (i) lead users are discoverable from large scale social media networks and (ii) product feature preferences, mined from lead user social media data, represent product features that do not currently exist in product offerings but will be desired in future product launches. An automated approach to lead user product feature identification is proposed to identify latent features (product features unknown to the public) from social media data. These latent features then serve as the key to discovering innovative users from the ever increasing pool of social media users. The authors collect 2.1 × 109 social media messages in the United States during a period of 31 months (from March 2011 to September 2013) in order to determine whether lead user preferences are discoverable and relevant to next generation cell phone designs.

scholarly journals Timing matters: crisis severity and occupancy rate forecasts in social unrest periods

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Richard T.R. Qiu ◽  
Anyu Liu ◽  
Jason L. Stienmetz ◽  
Yang Yu
Keyword(s):  
Social Media ◽  
Time Series ◽  
Hospitality Industry ◽  
Demand Forecasting ◽  
Time Series Model ◽  
Social Media Data ◽  
Forecasting Accuracy ◽  
Social Unrest ◽  
Content Type ◽  
Media Data

Purpose The impact of demand fluctuation during crisis events is crucial to the dynamic pricing and revenue management tactics of the hospitality industry. The purpose of this paper is to improve the accuracy of hotel demand forecast during periods of crisis or volatility, taking the 2019 social unrest in Hong Kong as an example. Design/methodology/approach Crisis severity, approximated by social media data, is combined with traditional time-series models, including SARIMA, ETS and STL models. Models with and without the crisis severity intervention are evaluated to determine under which conditions a crisis severity measurement improves hotel demand forecasting accuracy. Findings Crisis severity is found to be an effective tool to improve the forecasting accuracy of hotel demand during crisis. When the market is volatile, the model with the severity measurement is more effective to reduce the forecasting error. When the time of the crisis lasts long enough for the time series model to capture the change, the performance of traditional time series model is much improved. The finding of this research is that the incorporating social media data does not universally improve the forecast accuracy. Hotels should select forecasting models accordingly during crises. Originality/value The originalities of the study are as follows. First, this is the first study to forecast hotel demand during a crisis which has valuable implications for the hospitality industry. Second, this is also the first attempt to introduce a crisis severity measurement, approximated by social media coverage, into the hotel demand forecasting practice thereby extending the application of big data in the hospitality literature.

Sign in / Sign up

Export Citation Format

Share Document