===================================================================== --======== Review Reports ========-- The review report from reviewer #1: *1: Is the paper relevant to WI? [_] No [X] Yes *2: How innovative is the paper? [_] 5 (Very innovative) [X] 4 (Innovative) [_] 3 (Marginally) [_] 2 (Not very much) [_] 1 (Not) [_] 0 (Not at all) *3: How would you rate the technical quality of the paper? [_] 5 (Very high) [_] 4 (High) [X] 3 (Good) [_] 2 (Needs improvement) [_] 1 (Low) [_] 0 (Very low) *4: How is the presentation? [_] 5 (Excellent) [_] 4 (Good) [X] 3 (Above average) [_] 2 (Below average) [_] 1 (Fair) [_] 0 (Poor) *5: Is the paper of interest to WI users and practitioners? [X] 3 (Yes) [_] 2 (May be) [_] 1 (No) [_] 0 (Not applicable) *6: What is your confidence in your review of this paper? [_] 2 (High) [X] 1 (Medium) [_] 0 (Low) *7: Overall recommendation [_] 5 (Strong Accept: top quality) [X] 4 (Accept: a regular paper) [_] 3 (Weak Accept: could be a poster or a short paper) [_] 2 (Weak Reject: don't like it, but won't argue to reject it) [_] 1 (Reject: will argue to reject it) [_] 0 (Strong Reject: hopeless) *8: Detailed comments for the authors The paper focuses a very up to date topic of geo-mining big data . It considers how to infer user interests in POIs by collecting and analyzing the Internet traffic due to web services calls. The GeoEcho system is designed to this end that first identifies the georeference of web service calls , then associate these coordinates to close POIs in foursquare and finally from the user POI vector they derive a user interest vector. The approach is validated HTTP sessions to 2246 individual hosts withe a traffic trace. Some points need a clarification: 1) nothing is explained on the traffic tracer. How do you intercept Web service calls , the HTTP calls? 2) what are the a priori starting services you trust ? 3) how do you set the distance of user coordinates with POIs? 4) if some service provide a user position that is inaccurate, how do you compute a distance between POIs and an inaccurate user position? Why don't you use an inclusion or overlapping of the footprints? 5) the experiment is interesting but figures are too small to read. 6) you should deepen the privacy issue arisen by your proposal ======================================================== The review report from reviewer #2: *1: Is the paper relevant to WI? [_] No [X] Yes *2: How innovative is the paper? [_] 5 (Very innovative) [_] 4 (Innovative) [X] 3 (Marginally) [_] 2 (Not very much) [_] 1 (Not) [_] 0 (Not at all) *3: How would you rate the technical quality of the paper? [_] 5 (Very high) [_] 4 (High) [X] 3 (Good) [_] 2 (Needs improvement) [_] 1 (Low) [_] 0 (Very low) *4: How is the presentation? [_] 5 (Excellent) [X] 4 (Good) [_] 3 (Above average) [_] 2 (Below average) [_] 1 (Fair) [_] 0 (Poor) *5: Is the paper of interest to WI users and practitioners? [X] 3 (Yes) [_] 2 (May be) [_] 1 (No) [_] 0 (Not applicable) *6: What is your confidence in your review of this paper? [_] 2 (High) [X] 1 (Medium) [_] 0 (Low) *7: Overall recommendation [_] 5 (Strong Accept: top quality) [X] 4 (Accept: a regular paper) [_] 3 (Weak Accept: could be a poster or a short paper) [_] 2 (Weak Reject: don't like it, but won't argue to reject it) [_] 1 (Reject: will argue to reject it) [_] 0 (Strong Reject: hopeless) *8: Detailed comments for the authors The authors proposed a mobile traffic analysis system. The contribution of this paper includes: 1、The authors devise methods that effectively identify and prune irrelevant geo information and infer personal interests of individuals. 2、The results show that users show interest in a limited number of topics, and their interests are largely unique and stable over time. 3、The research problem of this paper is meaningful to user group analysis, advertising and so on. ======================================================== The review report from reviewer #3: *1: Is the paper relevant to WI? [_] No [X] Yes *2: How innovative is the paper? [_] 5 (Very innovative) [X] 4 (Innovative) [_] 3 (Marginally) [_] 2 (Not very much) [_] 1 (Not) [_] 0 (Not at all) *3: How would you rate the technical quality of the paper? [_] 5 (Very high) [X] 4 (High) [_] 3 (Good) [_] 2 (Needs improvement) [_] 1 (Low) [_] 0 (Very low) *4: How is the presentation? [_] 5 (Excellent) [X] 4 (Good) [_] 3 (Above average) [_] 2 (Below average) [_] 1 (Fair) [_] 0 (Poor) *5: Is the paper of interest to WI users and practitioners? [X] 3 (Yes) [_] 2 (May be) [_] 1 (No) [_] 0 (Not applicable) *6: What is your confidence in your review of this paper? [_] 2 (High) [X] 1 (Medium) [_] 0 (Low) *7: Overall recommendation [_] 5 (Strong Accept: top quality) [X] 4 (Accept: a regular paper) [_] 3 (Weak Accept: could be a poster or a short paper) [_] 2 (Weak Reject: don't like it, but won't argue to reject it) [_] 1 (Reject: will argue to reject it) [_] 0 (Strong Reject: hopeless) *8: Detailed comments for the authors This paper proposes a method for inferring user interests based on geotagging information passively collected from a number of services. The method consists o f several steps including the discovery of geotags in Internet traffic, the identification of actual user locations by filtering out noisy geotags, the determination of POIs corresponding to locations users visit, rather than places that are part of their daily routines, and the inference of their interests based on these POIs (based on Foursquare data). The results in a large sample dataset provide several useful insights that could be exploited by a variety of different applications. This is a very interesting research direction and the conducted investigation is very comprehensive as it addresses and provides solutions to many challenges in the overall pipeline of inferring interests from geotags and also performs an in depth analysis of the findings to provide useful insights. Evaluating such a method is very difficult, but the authors provide a reasonable validation of their approach in Section V-C. However, I had to read that section a few times to fully understand the validation strategy and I would suggest to the authors to provide some further details and possibly some examples to make it clearer. I also think that a small user study (with real volunteers, rather than anonymised users) would also be interesting for the further validation of the proposed approach and also its individual steps, which cannot be assessed otherwise. The paper is also very well structured and presented. There only some minor typos (e.g., "ash" --> "as") and grammar errors (e.g., "which only using" --> "which only use") that can be easily corrected by the authors after a careful read. ========================================================