Please use this identifier to cite or link to this item: https://hdl.handle.net/10419/52180 
Full metadata record
DC FieldValueLanguage
dc.contributor.authorHsu, Wenlingen
dc.contributor.authorJacobsen, Guyen
dc.contributor.authorJin, Yuen
dc.contributor.authorSkudlark, Annen
dc.date.accessioned2011-11-24T11:13:36Z-
dc.date.available2011-11-24T11:13:36Z-
dc.date.issued2011-
dc.identifier.urihttp://hdl.handle.net/10419/52180-
dc.description.abstractUnderstanding mobile customer experience and behavior is an important task for cellular service providers to improve the satisfaction of their customers. To that end, cellular service providers regularly measure the properties of their mobile network, such as signal strength, dropped calls, call blockage, and radio interface failures (RIFs). In addition to these passive measurements collected within the network, understanding customer sentiment from direct customer feedback is also an important means of evaluating user experience. Customers have varied perceptions of mobile network quality, and also react differently to advertising, news articles, and the introduction of new equipment and services. Traditional methods used to assess customer sentiment include direct surveys and mining the transcripts of calls made to customer care centers. Along with this feedback provided directly to the service providers, the rise in social media potentially presents new opportunities to gain further insight into customers by mining public social media data as well. According to a note from one of the largest online social network (OSN) sites in the US [7], as of September 2010 there are 175 million registered users, and 95 million text messages communicated among users per day. Additionally, many OSNs provide APIs to retrieve publically available message data, which can be used to collect this data for analysis and interpretation. Our plan is to correlate different sources of measurements and user feedback to understand the social media usage patterns from mobile data users in a large nationwide cellular network. In particular, we are interested in quantifying the traffic volume, the growing trend of social media usage and how it interacts with traditional communication channels, such as voice calls, text messaging, etc. In addition, we are interested in detecting interesting network events from users' communication on OSN sites and studying the temporal aspects - how the various types of user feedback behave with respect to timing. We develop a novel approach which combines burst detection and text mining to detect emerging issues from online messages on a large OSN network. Through a case study, our method shows promising results in identifying a burst of activities using the OSN feedback, whereas customer care notes exhibit noticeable delays in detecting such an event which may lead to unnecessary operational expenses.en
dc.language.isoengen
dc.publisher|aInternational Telecommunications Society (ITS) |cCalgaryen
dc.relation.ispartofseries|a22nd European Regional Conference of the International Telecommunications Society (ITS): "Innovative ICT Applications - Emerging Regulatory, Economic and Policy Issues", Budapest, Hungary, 18th-21st September, 2011en
dc.subject.jelC89en
dc.subject.jelL11en
dc.subject.ddc330en
dc.subject.keywordMobile customer experienceen
dc.subject.keywordsocial mediaen
dc.subject.keywordtext data miningen
dc.subject.keywordcustomer feedbacken
dc.titleUsing social media data to understand mobile customer experience and behavior-
dc.typeConference Paperen
dc.identifier.ppn672571285en
dc.rightshttp://www.econstor.eu/dspace/Nutzungsbedingungenen
dc.identifier.repecRePEc:zbw:itse11:52180en

Files in This Item:
File
Size
369.37 kB





Items in EconStor are protected by copyright, with all rights reserved, unless otherwise indicated.