lnu.sePublications
Change search
Link to record
Permanent link

Direct link
BETA
Rana, Juwel
Publications (10 of 19) Show all publications
Morshed, S. J., Rana, J. & Milrad, M. (2018). Active and Satisfied Users as a Key to Measure the Success of a Digital Mobile Service. In: Eunika Mercier-Laurent, Mieczysław L. Owoc, Nada Matta, Oliver Obst (Ed.), Proceedings 6th Artificial Intelligence for Knowledge Management (AI4KM), Stockholm, Sweden: . Paper presented at 6th Artificial Intelligence for Knowledge Management (AI4KM), 2018, Stockholm, Sweden.
Open this publication in new window or tab >>Active and Satisfied Users as a Key to Measure the Success of a Digital Mobile Service
2018 (English)In: Proceedings 6th Artificial Intelligence for Knowledge Management (AI4KM), Stockholm, Sweden / [ed] Eunika Mercier-Laurent, Mieczysław L. Owoc, Nada Matta, Oliver Obst, 2018Conference paper, Published paper (Refereed)
Abstract [en]

In order to develop, deploy and sustain a digital mobile service attractive to the users, one of the key parameters is to understand and to identify the satisfied users of such service and to maintain a user satisfaction-centric knowledge management. The classical way of achieving this is to collect users´ direct or indirect feedback and to measure their level of satisfaction. Digital mobile services have a global focus and address global audiences - which means getting users´ feedback and finding users´ satisfaction by performing studies using questionnaire for millions of users. Such an approach cannot be the most efficient way for doing so. This paper proposes an alternative approach of using data science knowledge and techniques, which performs a prediction on the usage data to distinguish between satisfactory and unsatisfactory users at a different level of granularity. First of all, this model generates some common predictors from users' access log data through descriptive analysis. Later, these predictive variables are used to predict the level of user satisfaction using Machine Learning Algorithms. Using this user-centric knowledge management model, digital service providers could measure whether their offered services would reach success by predicting the number of satisfied users.

Keywords
User feedback, digital service; user satisfaction; data science, prediction model; knowledge management, service evaluation, machine-learning algo-rithm;
National Category
Computer Sciences
Research subject
Computer and Information Sciences Computer Science, Computer Science
Identifiers
urn:nbn:se:lnu:diva-77508 (URN)
Conference
6th Artificial Intelligence for Knowledge Management (AI4KM), 2018, Stockholm, Sweden
Note

Ej belagd 180903

Available from: 2018-09-01 Created: 2018-09-01 Last updated: 2018-09-03Bibliographically approved
Noori, S. R., Hossain, M. K. K. & Rana, J. (2016). Key Indicators for Data Sharing - In Relation with Digital Services. In: DATA MINING AND BIG DATA, DMBD 2016: . Paper presented at 1st International Conference on Data Mining and Big Data (DMBD), JUN 25-30, 2016, Bali, INDONESIA (pp. 353-363). Springer
Open this publication in new window or tab >>Key Indicators for Data Sharing - In Relation with Digital Services
2016 (English)In: DATA MINING AND BIG DATA, DMBD 2016, Springer, 2016, p. 353-363Conference paper, Published paper (Refereed)
Abstract [en]

Rapid growth of data intensive digital services are creating potential risks of violating consumer centric data privacy. Protection of data privacy is becoming one of the key challenges for most of the big data business entities. Due to thank of big data, recommendation and personalization are becoming very popular in digital space. However it is hard to find a well-defined boundary which illustrates privacy threat to consumers' in relation with improving already opted-in communication services. In this paper, we initiated identifying key indicators for consumer configured privacy policy in relation with personalized services taking into consideration that "Privacy is a tool for balancing personalization". We survey user attitudes towards privacy and personalization and discovered key indicators for configuring privacy policy by analyzing survey data about privacy concern and data sharing attitude of the consumers. We found that consumers did not want to stop using social media based communication services due to privacy risks. Moreover, consumers have attitude of sharing their data, provided that appropriate personalization features are in place.

Place, publisher, year, edition, pages
Springer, 2016
Series
Lecture Notes in Computer Science, ISSN 0302-9743 ; 9714
Keywords
Data sharing, Big data driven digital services
National Category
Media and Communication Technology
Research subject
Computer and Information Sciences Computer Science, Media Technology
Identifiers
urn:nbn:se:lnu:diva-58207 (URN)10.1007/978-3-319-40973-3_35 (DOI)000386323800035 ()2-s2.0-85007560281 (Scopus ID)978-3-319-40973-3 (ISBN)978-3-319-40972-6 (ISBN)
Conference
1st International Conference on Data Mining and Big Data (DMBD), JUN 25-30, 2016, Bali, INDONESIA
Available from: 2016-11-18 Created: 2016-11-18 Last updated: 2019-08-09Bibliographically approved
Morshed, S. J., Rana, J. & Milrad, M. (2016). Open Source Initiatives and Frameworks Addressing Distributed Real-time Data Analytics. In: 2016 IEEE 30th International Parallel and Distributed Processing Symposium Workshops (IPDPSW): . Paper presented at 30th IEEE International Parallel and Distributed Processing Symposium (IPDPS), MAY 23-27, 2016, Illinois Inst Technol, Chicago, IL (pp. 1481-1484). IEEE
Open this publication in new window or tab >>Open Source Initiatives and Frameworks Addressing Distributed Real-time Data Analytics
2016 (English)In: 2016 IEEE 30th International Parallel and Distributed Processing Symposium Workshops (IPDPSW), IEEE, 2016, p. 1481-1484Conference paper, Published paper (Refereed)
Abstract [en]

The continuous evolution of digital services, is resulting in the generation of extremely large data sets that are created in almost real time. Exploring new opportunities for improving the quality of these digital services, as well as providing better-personalized experiences to digital users are two major challenges to be addressed. Different methods, tools, and techniques existed today to generate actionable insights from digital services data. Traditionally, big data problems are handled on historical data-sets. However, there is a growing demand on real-time data analytics to offer new services to users and to provide pro-active customers' care, personalized ads, emergency aids, just to give a few examples. Spite of the fact that there are few existing frameworks for real-time analytics, however, utilizing those for solving distributed real-time big data analytical problems stills remains a challenge. Existing real-time data analytics (RTDA) frameworks are not covering all the features that requires for distributed computation in real-time. Therefore, in this paper, we present a qualitative overview and analysis on some of the mostly used existing RTDA frameworks. Specifically, Apache Spark, Apache Flink, Apache Storm, and Apache Samza are covered and discussed in this paper.

Place, publisher, year, edition, pages
IEEE, 2016
Series
IEEE International Symposium on Parallel and Distributed Processing Workshops, ISSN 2164-7062
Keywords
Real-time, data analytics, big data, streaming data, data analytics framework, distributed real-time data analysis
National Category
Media and Communication Technology
Research subject
Computer and Information Sciences Computer Science, Media Technology
Identifiers
urn:nbn:se:lnu:diva-60583 (URN)10.1109/IPDPSW.2016.152 (DOI)000391253600182 ()2-s2.0-84991677313 (Scopus ID)978-1-5090-3682-0 (ISBN)
Conference
30th IEEE International Parallel and Distributed Processing Symposium (IPDPS), MAY 23-27, 2016, Illinois Inst Technol, Chicago, IL
Available from: 2017-02-08 Created: 2017-02-08 Last updated: 2018-01-13Bibliographically approved
Morshed, S. J., Rana, J. & Milrad, M. (2016). Real-Time Data Analytics: An Algorithmic Perspective. In: DATA MINING AND BIG DATA, DMBD 2016: . Paper presented at 1st International Conference on Data Mining and Big Data (DMBD), JUN 25-30, 2016, Bali, INDONESIA (pp. 311-320). Springer
Open this publication in new window or tab >>Real-Time Data Analytics: An Algorithmic Perspective
2016 (English)In: DATA MINING AND BIG DATA, DMBD 2016, Springer, 2016, p. 311-320Conference paper, Published paper (Refereed)
Abstract [en]

Massive amount of data sets are continuously generated from a wide variety of digital services and infrastructures. Examples of those are machine/system logs, retail transaction logs, traffic tracing data and diverse social data coming from different social networks and mobile interactions. Currently, the New York stock exchange produces 1 TB data per day, Google processes 700 PB of data per month and Facebook hosts 10 billion photos taking 1 PB of storage just to mention some cases. Turning these streaming data flow into actionable real-time insights is not a trivial task. The usage of data in real-time can change different aspects of the business logic of any corporation including real time decision making, resource optimization, and so on. In this paper, we present an analysis of different aspects related to real-time data analytics from an algorithmic perspective. Thus, one of the goals of this paper is to identify some new problems in this domain and to gain new insights in order to share the outcomes of our efforts and these challenges with the research community working on real-time data analytics algorithms.

Place, publisher, year, edition, pages
Springer, 2016
Series
Lecture Notes in Computer Science, ISSN 0302-9743 ; 9714
Keywords
Big data, Real-time data analytics, Machine learning algorithms, Large-scale stream data processing
National Category
Media and Communication Technology
Research subject
Computer and Information Sciences Computer Science, Media Technology
Identifiers
urn:nbn:se:lnu:diva-58206 (URN)10.1007/978-3-319-40973-3_31 (DOI)000386323800031 ()2-s2.0-85007454156 (Scopus ID)978-3-319-40973-3 (ISBN)978-3-319-40972-6 (ISBN)
Conference
1st International Conference on Data Mining and Big Data (DMBD), JUN 25-30, 2016, Bali, INDONESIA
Available from: 2016-11-18 Created: 2016-11-18 Last updated: 2018-01-13Bibliographically approved
Sotsenko, A., Jansen, M., Milrad, M. & Rana, J. (2016). Using a Rich Context Model for Real-Time Big Data Analytics in Twitter. In: 2016 IEEE 4TH INTERNATIONAL CONFERENCE ON FUTURE INTERNET OF THINGS AND CLOUD WORKSHOPS (FICLOUDW): . Paper presented at IEEE 4th International Conference on Future Internet of Things and Cloud Workshops (FiCloudW), AUG 22-24, 2016, Vienna, AUSTRIA (pp. 228-233). IEEE
Open this publication in new window or tab >>Using a Rich Context Model for Real-Time Big Data Analytics in Twitter
2016 (English)In: 2016 IEEE 4TH INTERNATIONAL CONFERENCE ON FUTURE INTERNET OF THINGS AND CLOUD WORKSHOPS (FICLOUDW), IEEE, 2016, p. 228-233Conference paper, Published paper (Refereed)
Abstract [en]

In this paper we present an approach for contextual big data analytics in social networks, particularly in Twitter. The combination of a Rich Context Model (RCM) with machine learning is used in order to improve the quality of the data mining techniques. We propose the algorithm and architecture of our approach for real-time contextual analysis of tweets. The proposed approach can be used to enrich and empower the predictive analytics or to provide relevant context-aware recommendations.

Place, publisher, year, edition, pages
IEEE, 2016
Keywords
rich context model, big data, context analytics, twitter, k-means clustering
National Category
Media and Communication Technology
Research subject
Computer and Information Sciences Computer Science, Media Technology
Identifiers
urn:nbn:se:lnu:diva-58342 (URN)10.1109/W-FiCloud.2016.55 (DOI)000386667700037 ()2-s2.0-85009830198 (Scopus ID)978-1-5090-3946-3 (ISBN)978-1-5090-3947-0 (ISBN)
Conference
IEEE 4th International Conference on Future Internet of Things and Cloud Workshops (FiCloudW), AUG 22-24, 2016, Vienna, AUSTRIA
Available from: 2016-11-30 Created: 2016-11-28 Last updated: 2019-06-05Bibliographically approved
Rana, J., Bjelland, J., Sundsoy, P., Couronne, T., Qureshi, T. & Canright, G. (2015). Smartphone applications co-usage: Could we predict your next app?. In: Network Science x2015: . Paper presented at Network Science x2015, NetSci-x2015, June 1-5, 2015, Zaragoza.
Open this publication in new window or tab >>Smartphone applications co-usage: Could we predict your next app?
Show others...
2015 (English)In: Network Science x2015, 2015Conference paper, Poster (with or without abstract) (Refereed)
Abstract [en]

Smartphone applications are becoming part of our everyday life. Cost of smartphone devices is dropping and development of smartphone applications is getting simpler. Moreover, these applications are spanning from entertainment to education, health, productivity, finance, payment, transportation - and much more. Based on a study of handset usage analytics we find that users are spending more than 88 minutes with direct interaction of their devices’ screen, and initiates at least 38 Apps on a daily basis. Until September 2014, Apple Store has 1.3 million of active Apps and a cumulated download number of 75 billion apps. Google Play also shows similar volumes. In summary, these numbers lead us towards the era where our daily activities would be Apps centric, and our productivity would be driven by an appropriate selection of Apps. 

National Category
Media and Communication Technology
Research subject
Computer and Information Sciences Computer Science, Media Technology
Identifiers
urn:nbn:se:lnu:diva-41713 (URN)
Conference
Network Science x2015, NetSci-x2015, June 1-5, 2015, Zaragoza
Available from: 2015-04-05 Created: 2015-04-05 Last updated: 2018-01-11Bibliographically approved
Rana, J., Bjelland, J., Couronne, T., Sundsoy, P., Wagner, D. & Rice, A. (2014). A Handset-centric View of Smartphone Application Use. In: 9TH INTERNATIONAL CONFERENCE ON FUTURE NETWORKS AND COMMUNICATIONS (FNC'14) / THE 11TH INTERNATIONAL CONFERENCE ON MOBILE SYSTEMS AND PERVASIVE COMPUTING (MOBISPC'14) / AFFILIATED WORKSHOPS: . Paper presented at The 11th International Conference on Mobile Systems and Pervasive Computing (MobiSPC'14) (pp. 368-375). Amsterdam: Elsevier, 34
Open this publication in new window or tab >>A Handset-centric View of Smartphone Application Use
Show others...
2014 (English)In: 9TH INTERNATIONAL CONFERENCE ON FUTURE NETWORKS AND COMMUNICATIONS (FNC'14) / THE 11TH INTERNATIONAL CONFERENCE ON MOBILE SYSTEMS AND PERVASIVE COMPUTING (MOBISPC'14) / AFFILIATED WORKSHOPS, Amsterdam: Elsevier, 2014, Vol. 34, p. 368-375Conference paper, Published paper (Refereed)
Abstract [en]

Studying the use of applications on smart phones is important for developers, handset designers and network operators. We conducted a study on Android devices by installing an instrumentation application, Device Analyzer, on participants’ handsets. Over a 4 month period we collected 10.9 billion records from 674 different users. In this paper we describe how to use the research study features of Device Analyzer to control participant selection and to access information (with consent) that is withheld for privacy reasons from the main dataset. We describe our data processing architecture and the steps required to preformat and analyse the data. Our data contains 3329 distinct applications (from the Google Play store) but despite this, on average, a user makes use of only 8 unique applications in a week. Almost 100% of our users make use of some email application on their phone. Fewer users (85%) made use of the Facebook application but 4–5 times more frequently than for email with sessions lasting almost twice as long. We also investigated whether different applications have correlated usage using a network analysis and a principal component analysis. We see that application usage tends to correlate by vendor more than by activity. This is potentially due to vendors integrating or cross-promoting services between applications.

Place, publisher, year, edition, pages
Amsterdam: Elsevier, 2014
Series
Procedia Computer Science, ISSN 1877-0509 ; 34
National Category
Media and Communication Technology
Research subject
Computer and Information Sciences Computer Science, Media Technology
Identifiers
urn:nbn:se:lnu:diva-41706 (URN)10.1016/j.procs.2014.07.039 (DOI)000349979900045 ()
Conference
The 11th International Conference on Mobile Systems and Pervasive Computing (MobiSPC'14)
Available from: 2015-04-04 Created: 2015-04-04 Last updated: 2018-01-11Bibliographically approved
Rana, J., Kristiansson, J. & Synnes, K. (2014). Data Matters: Reflection on User Defined Social Prioritization. In: ASE@360 Open Scientific Digital Library: . Paper presented at 2014 ASE BIGDATA/SOCIALCOM/CYBERSECURITY Conference, Stanford University, May 27-31, 2014. ASE@360
Open this publication in new window or tab >>Data Matters: Reflection on User Defined Social Prioritization
2014 (English)In: ASE@360 Open Scientific Digital Library, ASE@360 , 2014Conference paper, Published paper (Refereed)
Abstract [en]

Online social networking becomes an integral part of our everyday life and thus, social computing is get- ting huge attention in these years. One of the areas of social computing is to understand humans' social or tie strength by observing measurable social interactions. Thanks to today's communication and social media services that open tremendous opportunities for communicating through electronic media, such as through mobile phone calls, SMS, emails, or social media tools. That has made it possible to automatically measure and predict human's social strength. The social strength is defined as a metric that represents the tie strength of the relation between persons, calculated based on the frequency, duration, context and media type of the electronic communication be- tween the persons. For example, a family relation is generally considered to be stronger than a relation between coworkers in our society, but the strength of the relation is intrinsic and have been cumbersome to measure. This paper thus presents reflection of user- defined ranking of social prioritization in comparison with machine defined social strength. The study found that there is significant difference in results between the algorithmic and the user-defined strength ranking, which indicates the inability of the algorithms to capture intrinsic knowledge (such as the importance of family bonds and non-electronic interaction). This would mean that the participants' ranking was colored by their interaction in real-life. This study also found several implications, in which diverse source and volume of interaction data are considered as key performance issues for algorithmic strength ranking.

Place, publisher, year, edition, pages
ASE@360, 2014
Keywords
Data, Social networking, Euclidean Distance, Prediction
National Category
Media and Communication Technology
Research subject
Computer and Information Sciences Computer Science, Media Technology
Identifiers
urn:nbn:se:lnu:diva-41712 (URN)978-1-62561-000-3 (ISBN)
Conference
2014 ASE BIGDATA/SOCIALCOM/CYBERSECURITY Conference, Stanford University, May 27-31, 2014
Available from: 2015-04-05 Created: 2015-04-05 Last updated: 2018-01-11Bibliographically approved
Rana, J., Kristiansson, J. & Synnes, K. (2014). Modeling unified interaction for communication service integration. In: Jaime Lloret Mauri (Ed.), The Fourth International Conference on Mobile Ubiquitous Computing, Systems, Services and Technologies : UBICOMM 2010: . Paper presented at The Fourth International Conference on Mobile Ubiquitous Computing, Systems, Services and Technologies : UBICOMM 2010 (pp. 373-378). Red Hook, NY: Curran Associates, Inc.
Open this publication in new window or tab >>Modeling unified interaction for communication service integration
2014 (English)In: The Fourth International Conference on Mobile Ubiquitous Computing, Systems, Services and Technologies : UBICOMM 2010 / [ed] Jaime Lloret Mauri, Red Hook, NY: Curran Associates, Inc., 2014, p. 373-378Conference paper, Published paper (Refereed)
Abstract [en]

Social network inspired communication services has made a huge success, allowing users to communicate and share information in new fashion. At the same time, telecom operator's services are becoming more open, which makes it possible to develop improved social networking services and integrate them with mobile platforms. One problem that needs to be addressed when developing such services how to fetch useful social information and make it available for the services running in the cloud or in the client devices. This paper presents a generalized on-line interaction model that collects useful information from well known social networking services, and transforms the information into unified interaction patterns, which can be utilized for social data propagation or for discovering communication patterns. Ultimately, this allows the applications to incorporate social data for enabling smarter functions. For example, the data model can be useful for presenting information about callers or adding news feeds to the classical address book, prioritizing information of the contacts, inviting user for forming micro-communities. The paper also discusses the identity problem in the social media and identifies major challenges to solve that problem

Place, publisher, year, edition, pages
Red Hook, NY: Curran Associates, Inc., 2014
National Category
Media and Communication Technology
Research subject
Computer and Information Sciences Computer Science, Media Technology
Identifiers
urn:nbn:se:lnu:diva-41857 (URN)978-1-61208-000-0 (ISBN)
Conference
The Fourth International Conference on Mobile Ubiquitous Computing, Systems, Services and Technologies : UBICOMM 2010
Available from: 2015-04-08 Created: 2015-04-08 Last updated: 2018-01-11Bibliographically approved
Rana, J., Kristiansson, J. & Synnes, K. (2014). The strength of social strength: an evaluation study of algorithmic versus user-defined ranking. In: SAC '14 Proceedings of the 29th Annual ACM Symposium on Applied Computing: . Paper presented at 29th Annual ACM Symposium on Applied Computing (pp. 658-659). ACM Press
Open this publication in new window or tab >>The strength of social strength: an evaluation study of algorithmic versus user-defined ranking
2014 (English)In: SAC '14 Proceedings of the 29th Annual ACM Symposium on Applied Computing, ACM Press, 2014, p. 658-659Conference paper, Published paper (Refereed)
Abstract [en]

A family relation is generally considered to be stronger than a relation between coworkers in our society, but the strength of the relation is intrinsic and have been cumbersome to measure. The fact that we increasingly communicate electronically, such as through email, mobile phone calls or social media, has made it possible to automatically measure and analyze the relation between persons. This paper presents an evaluation study of social strength, where the social strength is defined as a metric that represents the tie strength of the relation between persons, calculated based on the frequency, duration, context and media type of the electronic communication between the persons.

The study found that the Utility Function performs better because it emphasize the communication frequency between persons. There is however a significant difference in results between the algorithms and the user-defined ranking. This indicates the inability of the algorithms to capture intrinsic knowledge (such as the importance of family bonds and non-electronic interaction). This would mean that the participants' ranking was colored by their interaction in real-life. It is however evident from the study that the functions provide more accurate results when they utilize multiple sources of communication history over only a single source.

Finally, capturing sufficient communication data from multiple data sources is very hard, as access to such data is restricted because of concerns regarding for instance business and privacy. A conclusion is that the algorithms requires a larger data set, preferably being captured continuously over a period longer than 2 weeks, to achieve a better accuracy that is closer to the ground truth. However, the study shows the feasibility of capturing social strength automatically and we believe that the results is an important step towards systems that reason about the relation between persons in order to make communications services more pervasive.

Place, publisher, year, edition, pages
ACM Press, 2014
National Category
Electrical Engineering, Electronic Engineering, Information Engineering
Research subject
Computer and Information Sciences Computer Science, Media Technology
Identifiers
urn:nbn:se:lnu:diva-41707 (URN)10.1145/2554850.2555158 (DOI)978-1-4503-2469-4 (ISBN)
Conference
29th Annual ACM Symposium on Applied Computing
Available from: 2015-04-04 Created: 2015-04-04 Last updated: 2015-04-22Bibliographically approved
Organisations

Search in DiVA

Show all publications