Frequency and recency context for the management and retrieval of personal information on mobile devices

Stefanis, Vassileios; Πλέσσας, Αθανάσιος; Komninos, Andreas; Garofalakis, John

doi:10.1016/j.pmcj.2013.08.002

Cited by 14 publications

(19 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The researchers performed an evaluation of their application with only one participant and only for a short period (12 days) without actually examining the impact of any of the individual contextual cues to the prediction performance. Although such a limited evaluation cannot provide reliable results, we should note that the inclusion of location did not seem to improve performance, as the reported prediction accuracy is close to that presented in [15] and [7] (around 70% for 5 suggestion entries).…”

Section: Related Workmentioning

confidence: 74%

“…In a previous publication [7] we performed a preliminary experiment to evaluate the effect of temporal context on prediction accuracy. Temporal context can be used to detect patterns of movements and semantic information about location.…”

Section: Discussionmentioning

confidence: 99%

“…We decided to reject from our analysis users with less than 70% of geolocated call records as we believe that keeping users below this threshold could prove harmful for the reliability of our prediction algorithm results. Moreover, we excluded users that could not be considered valid for call log analysis, since some of them had a call log covering an extremely short period of time (less than 30 days), while others had too few call records (less than 100) or a very sparse call usage of their phone (less than 2.25 calls per day), a procedure also followed while carrying out the experiments described in our previous work [7]. These extreme characteristics can be explained, since there were users who left the experiment early or others who often decided to turn off the recording software, according to the dataset's documentation.…”

Section: A Datasetmentioning

confidence: 99%

“…Such solutions require a context aware algorithm that predicts at any time the next contact to be called. In previous work [6] [7], we proposed such an algorithm that uses the context dimensions of frequency and recency of communication and whose top suggestions feed a speed dial list, facilitating contact retrieval [8].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Assessing Physical Location as a Potential Contextual Cue For Adaptive Mobile Contact Lists

Πλέσσας

Georgiadou

Stefanis

et al. 2015

2015 IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable,

Self Cite

View full text Add to dashboard Cite

Abstract-The retrieval of the appropriate contact in order to start a new communication session from the contact repository of mobile devices can be a time consuming procedure since mobile contact lists usually contain hundreds of items. Several researchers have focused in the past on predicting the next contact a user is likely to call, a task that could prove useful in designing adaptive context-aware interfaces for the mobile contact list. Most of the researchers propose several contextual dimensions that could be used to predict the next callee, location being one of them. However, none of these research works have ever examined the impact of location on mobile communications and only few have actually incorporated this contextual dimension on their implementations. In this paper, we examine physical location as a contextual cue for adaptive mobile contact lists by analyzing call logs from the Nokia Mobile Data Challenge dataset. Our work indicates that, contrary to previous literature, the consideration of physical location as a context dimension does not necessarily lead to improvements in the accuracy of predicting the likelihood of communication with contacts for all types of users included in the dataset under review. Finally, we also discuss the possible reasons behind this limited impact.

show abstract

Section: Related Workmentioning

confidence: 74%

Section: Discussionmentioning

confidence: 99%

Section: A Datasetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Assessing Physical Location as a Potential Contextual Cue For Adaptive Mobile Contact Lists

Πλέσσας

Georgiadou

Stefanis

et al. 2015

2015 IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable,

Self Cite

View full text Add to dashboard Cite

show abstract

“…For that, adaptive interfaces exploiting the mobile context led to context-aware algorithms that predict at any time the next callee. In [26,27], were proposed contextaware algorithms that used frequency and recency of communication as context cues. In [28], physical location was examined as a context cue for predicting the next callee.…”

Section: Related Workmentioning

confidence: 99%

On a Mobile Phone Contact List Based on Social Relations

Poda¹,

Zongo²,

Dagnogo³

et al. 2018

EAI Endorsed Transactions on Smart Cities

View full text Add to dashboard Cite

Social relations are unquestionably the major provider of contacts in the mobile devices contact lists. However, they remain marginal in the literature of social software related to the contact list and are not at all integrated in its design. Inspired by African social and cultural practices, this paper is about a design of the contact list that integrates the social relationships existing between people in the real life. A desktop prototype of the proposed contact list designing allows to validate it. Illustrations of the developed application demonstrate the assets of the proposed contact list regarding issues such as contacts reminding/retrieval and homonymy resolving with respect to the real life. Additional capabilities of the proposed contact list reside in the creation of groups of contacts for group communications needs.

show abstract