FOUR ASPECTS OF RELEVANCE IN SHARING

LOCATION-BASED MEDIA: CONTENT, TIME,

LOCATION AND NETWORK

Pasi Fränti, Jinhua Chen and Andrei Tabarcea

Speech & Image Processing Unit, School of Computing, University of Eastern Finland, Joensuu, Finland

Keywords: Data sharing, Relevance, Location-based applications.

Abstract: Sharing information via internet is popular but the key problem is how to find relevant information. Two

new features are becoming more popular: location and the social network of the user. We hypothesize that

the relevance of data is defined by four aspects: content, time, location, and user network. We study how the

location aspect is used in a media-sharing service called MOPSI.

1 INTRODUCTION

Location-based services are becoming widely used

due to the fast development of positioning systems

in multimedia phones. Location provides additional

information that can be expressed as a point of

interest, route, or geographic area. The location can

be considered information as itself but it is often

attached to other data, and shared via location-based

service or photo sharing site.

GPS

Data collector:

www

Other users:

MOPSI

webpage

Service

directory

N 62.63 E 29.86

User

collection

Last skiing of winter

User: Pasi

Figure 1: Diagram of the MOPSI data collection and

services. Available on-line: http://cs.joensuu.fi/mopsi/.

In this paper, we study mobile location-based

media sharing via internet by a case study based on

MOPSI service, which is prototype service for

sharing location-based media. The overall structure

of the system is outlined in Fig. 1 consisting of two

main parts: user collection and service directory.

The main limitation of this kind of ad hoc

information sharing is unawareness of the material

of others especially if the users are not directly

linked with each other. The data itself may be

available in the service but the problem is how to

find relevant data from service with a large number

of users. We argue that relevance can be defined by

the following aspects:

(1) Content of the data

(2) Location

(3) Time

(4) Author and his/her network

Last skiing of winter

Date: 4.4.2010

Location: N 62.63 E 29.86

Arppentie 5, Joensuu

User: Pasi

 Keywords: skis, forest, snow

 Informal description

 Relevance defined by

the network of the user

 Date and time

(not expected in July)

1. Content

2. Time

3. Location

4. Social network

 Exact coordinates

 Address for usability

Figure 2: Four aspects of relevance in practice.

These four aspects are demonstrated in Fig. 2 by

a concrete example where a person wanted to

capture the following scenario. From the photo and

its description we can see skis, forest and snow,

which relate to wintertime activity. The data also

reveals when and where the picture was taken. In 4

413

Fränti P., Chen J. and Tabarcea A..

FOUR ASPECTS OF RELEVANCE IN SHARING LOCATION-BASED MEDIA: CONTENT, TIME, LOCATION AND NETWORK.

DOI: 10.5220/0003342704130417

In Proceedings of the 7th International Conference on Web Information Systems and Technologies (WEBIST-2011), pages 413-417

ISBN: 978-989-8425-51-5

 2011 SCITEPRESS (Science and Technology Publications, Lda.)

April 2010, there was skiing tracks available, which

was not self-evident even for citizens of Joensuu.

Knowing a proper location was essential. The last

piece of information is the identity of the user

himself. Strangers may not benefit much of this

information but those who know him and share the

same hobbies are more likely to find this useful.

2 CONTENT, TIME AND

LOCATION

We discuss the three main aspects of MOPSI

system, of which location is an essential part. We

describe the system as its current state, and discuss

its design alternatives.

2.1 Content

Traditionally the relevance is defined by the content

either by user-given keywords, or using a predefined

format in database system, and then retrieved using

SQL queries. This requires well-designed static

database where the service provider models the user

behavior beforehand and provides information in

form of service directory.

In internet, well-defined attributes are not used

but relevant content can still be found from free text

using search engine if the content matches to the

keywords provided by the user. Tagging of the

photos can also be done afterwards, but usually free-

form textual explanation is simpler. It also serves the

purpose of social media.

In MOPSI, free-form text description is

supported instead of manual tagging. For browsing

the data on web, queries based on time, location and

content have been implemented. A simple

recommendation framework is also in MOPSI based

on user location and rating of the photos.

Further analysis of the relevance, content-based

image retrieval could be done based on color, texture

and shape features. Automatic image categorization,

aims at converting visual content into a set of

keywords to describe the content. In (Choudhury et

al., 2009, Yu et al., 2009) both visual content and

user tagging are jointly applied to recommend the

group, where a photo should best fit in.

2.2 Location

Exploiting the location of the user has become

popular due to wide availability of GPS positioning

in multimedia phones. In case of lacking GPS,

positioning can also be provided by cellular network

of mobile phone, or even using the IP address for a

rough estimation of location. Once the location is

known, it gives significant additional relevance that

can be utilized in several different ways. In MOPSI,

location is the key element and it provides additional

relevance in the following ways:

(1) Browsing data collection on a map

(2) Show location of other users

(3) Track the movements of the user

(4) Filter relevant search results for the service

directory

Fig. 3 demonstrates the map view in MOPSI

where photos have been clustered and then shown

using GoogleMaps API.

Figure 3: Map view of the data collection.

Location of users has been visualized in Fig. 4

using a so-called smart swap algorithm (Chen et al.,

2010) that provides accurate clustering in real-time.

For representing the clusters, approaches using

icons, grids, Voronoi diagrams, and coloring by the

Figure 4: Map view of user locations.

WEBIST 2011 - 7th International Conference on Web Information Systems and Technologies

414

density have been considered in (Delort, 2010). We

use a color bubble attached with the text

representing the most recent users in the cluster. The

browsing is supported by zooming operation to get

inside bigger clusters. Details of this solution will be

reported later elsewhere.

The collection can also be used as a part of

service directory in MOPSI either in mobile phone

or on web, see Fig. 5. Given location, user makes

query by keyword, but instead of providing relevant

search results by the content alone, results nearby

are given if they exist in a local database (green), or

found in the user collection (yellow).

Additional information (red) is provided by

location-based search (Fränti et al., 2010), which is

a combination of traditional location-based service

and search engine. Following the idea in (Huitema

and Fizzano, 2010), MOPSI allows user to transfer

search engine results (red) into the service directory

(green) by adding proper keywords similarly, and by

using photos from the user collection (yellow).

Database

results

Search engine

results

Results from

user collection

Figure 5: Web page interface to the service directory.

2.3 Time

Time can be added to the relevance of the data in

several ways. Firstly, the information may be

relevant only within certain time period. A concert

or a sport event happens in certain time and day, and

it is essential information for participants. In photo

collection, the information can also be relevant to

know when the photo was taken. In MOPSI

collection, we utilize this by providing time line

view to the data as shown in Fig. 6. Similar layout

was considered in (Setlur et al., 2009), with the

addition that also links to Wikipedia are supported to

provide more information besides just the photos.

Secondly, the time and location themselves can

be the essential data from an exercise session. For

example, the jogging track shown in Fig. 7 records

the length, duration and average speed. This is

typical book-keeping for a long distance runner in

his training. Although specialized GPS sport trackers

exist, the use of MOPSI service and mobile phone

allows automatic sending of the data into the server

Figure 6: Time-line view of the data collection.

Figure 7: Joint time and location for tracking sport

activity.

for user convenience. Moreover, photos can also be

taken from the same session by the same device, and

presented later jointly with the trajectory of the user

as proposed in (Petit et al., 2008).

In MOPSI collection, tracking user’s routes is

one of the main functions. The web interface

provides also navigation from the current location to

the location of the search result using GoogleMaps

API based on road maps. An interesting idea for

future consideration would be to use the route

collection of all users to offer better navigation for

pedestrians and hikers instead of the road network

more suitable for cars (Kasemsuppakorn et al.,

2009).

Third possibility to utilize the time information is

to consider the age of data. The newer the

information the more likely it is still valid as the life

expectancy of cafeterias, for example, in typical

metropolitan area are often measured in months

rather than in years. Moreover, information such as

weather condition is needed right here and right

FOUR ASPECTS OF RELEVANCE IN SHARING LOCATION-BASED MEDIA: CONTENT, TIME, LOCATION AND

NETWORK

415

now, so to speak. In Fig. 1, the skiing condition is

recorded for 4

April, but it hardly relevant for users

in July.

3 EXPERIMENTS

We next give overview of the data in the user

collection so far as on 25

October 2010. The

collection includes lots of test photos, and the

number of users is small, which may somewhat

skew the results. Nevertheless, some trends and

observations can be seen.

In total, there were 3589 photos of which most

are city views (839), then pictures of nature (801)

and other people (279). Few pictures are also taken

from events (90), documents (40) and animals (59).

In addition, there are photos that are counted as test

photos or failure pictures.

Another point of view is what kind of

descriptions has been typed in by the users. Due to

the experimental stage, a large amount of the photos

(27%) are without any description. The lack of

descriptions is also caused by the difficulty to type

by mobile phone, but descriptions can be added later

from the web interface.

Among the photos that have some kind of

description, significant amount of photos (35%)

have just garbage, some test word (Symbian_test), or

very generic object description (Mug, Wires, Mouse)

indicating test use. In total, 65% of all photos have a

meaningful description. Mostly documented

descriptions are travel photos of places (685), nature

(579), general objects (263), architecture (212)

people (210), and few general descriptions of events

and animals.

People are often described by their names, or by

their roles (runner, floorball player). Only few are

related to place (Untung / STMIK), age (Young

Andrei) or relationship to the person (my son Amir).

Events are significantly more often found in the

user description than could be concluded by content

analysis alone. In our case, events include mostly

work-related meetings described by their acronyms

(ecse, abi, mopsi meeting, ubiikki) but also running

competition (Åland half marathon) and actions

attached with feelings (quality time in skiing

elevator).

Another difference between content and user

description are travel photos. The location is not

easy to recognize from content but it could be

concluded from the positioning data. For example,

Clarke Quay, Geger beach, Suceava, Tahkovuori

and Aholansaari are locations whereas the following

descriptions include additional details: Petronas

Towers (building complex), Heureka (science

center), Singapore flier (Ferris wheel) and Olavin

linna (castle). The extreme case is Musta Pekka

mutkan takana (Black Pete behind the curve) where

Black Pete is the name of a particular slope in Tahko

skiing resort.

Table 1: Distribution of keywords (tags) used in Picasa

and Flickr, in comparison to the user descriptions of

MOPSI collection.

Description:

Picasa Flickr

MOPSI

All Real

Places --- 28% 21% 32%

Events and action 31% 17% 5% 7%

People 6% 7% 6% 10%

Objects --- 5% 8% 12%

Architecture and

nature

25% 21% 23% 37%

Animals --- 3% 2% 2%

Other 20% 16% --- 0%

Garbage 19% 2% 35% ---

Table 1 compares the textual description used in

MOPSI with two other photo sharing sites. The main

difference is that, in MOPSI, location is provided

automatically without any user interaction.

In Picasa, users provide the location by dragging

the photo on GoogleMap. Keywords and location

are thus provided explicitly as two different entities,

and consequently, users tend not to type any location

related keywords. Flickr has somewhat more

complicated interface based on Yahoo! Maps. Only a

predefined set of keywords are allowed, which

explains the quality of tags (only 2% garbage).

Despite the automatic positioning in MOPSI, it

does not reflect on the distribution of the type of

descriptions written. Unlike in Picasa, users still tend

to describe the location anyway for travel pictures,

probably because the position is not confirmed in the

device, but it happens hidden in the background.

Overall, the distribution of topics is rather similar to

that of Flickr. There are slightly more people and

objects described, but these could be just artifacts

from the system being at testing stage.

For photo collecting, two mobile applications

were developed (Java and Symbian C++). A large

number of failures were caused by the Java version,

which lacks several important features. Firstly, there

is an unavoidable delay from the click sound and

when the photo is actually taken. People tend to

move the camera right after they hear the sound and

before the actual picture will be taken. Secondly,

Auto-focus supported by Symbian helps a lot with

picture quality but it was not available in Java. Other

WEBIST 2011 - 7th International Conference on Web Information Systems and Technologies

416

typical failures originate from low quality cameras

that do not work well in low illumination. Few

damaged pictures were caused by irrecoverable

transmission error. Samples are shown in Fig. 8.

Failure photo Still useful

Low illumination Broken transmission

Singapore flier (Going to) Sauna

No keywords needed No keywords needed

Figure 8: Photos of the first row are examples of software

problems (click sound), the second row of low

illumination and broken transmission problems. The rest

are successful photos.

4 CONCLUSIONS

We have presented a case study of MOPSI location-

based media collection and sharing service, and

studied how different aspects of relevance appear in

the system. So far the system has been used for

collecting user data (mainly photos and routes),

served as a test bench of new ideas, and a prototype

service directory. In all these, the location is a key

factor.

The media collection tool is also in professional

use by partnering companies for documenting

purpose, and can be used later for mobile location-

based games and an educational tool for teaching

principles of GIS, and other classes such as biology.

The fourth aspect of relevance, social network, will

be studied in future.

REFERENCES

Choudhury M. D., Sundaram H., Lin Y.-R., John A.,

Seligmann D.D., “Connecting content to community

in social media via image content, user tags and user

communication”, ICME 2009, 1238-1241, New York

City, July 2009.

Yu J., Joshi D., Luo J., “Connecting people in photo-

sharing sites by photo content and user annotations”,

ICME 2009, 1464-1467, New York City, July 2009.

Chen J., Zhao Q., and Fränti P., "Smart swap for more

efficient clustering", Int. Conf. Green Circuits and

Systems (ICGCS’10), Shanghai, China, June 2010.

Delort J.-Y., “Vizualizing large spatial datasets in

interactive maps”, IEEE Int. Conf. Advanced

Geographic Information Systems, Applications, and

Services, St. Maarten, Netherlands Antilles, 33-38,

Feb 2010.

Fränti P. , Tabarcea A., Kuittinen J., Hautamäki V.,

“Location-based search engine for multimedia

phones”, IEEE Int. Conf. on Multimedia & Expo

(ICME’10), Singapore, July 2010.

Huitema P. and Fizzano P., “A Crawler for Local Search”,

IEEE Int. Conf. Digital Society (ICDS), St. Maarten,

Netherlands Antilles, 86-91, Feb 2010.

Setlur V., Battestini A., Ding X., “Travel scrapbooks:

creating rich visual travel narratives”, ICME 2009,

1314-1317, New York City, July 2009.

Petit M., Claramunt C., Ray C. and Calvary G., “A design

process for the development of an interactive and

adaptive GIS”, W2GIS, 96-106, Shanghai, China 2008.

Kasemsuppakorn P., Karimi H.A., “Pedestrian network

data collection through location-based social

networks”, Collaborate COM, Crystal City,

Washington DC, Nov 2009.

FOUR ASPECTS OF RELEVANCE IN SHARING LOCATION-BASED MEDIA: CONTENT, TIME, LOCATION AND

NETWORK

417