*****  To join INSNA, visit http://www.insna.org  *****
<div dir="ltr">Carlos, muchos gracias. (That is, I&#39;m afraid, the end of my Spanish).<div><br></div><div style>I have just downloaded the Santo Fortunato article and am looking forward to reading it.</div><div style><br>
</div><div style>I should add to what I have written in other messages that I am continuing to work on a problem that I talked about at the Sunbelt Conference in Hamburg. I have a body of data — networks of award-winning ads and the creators who produced them, sampled at five-year intervals—from an industry I know a good deal about, partly from recent historical and ethnographic research, and partly because I worked for one of Japan&#39;s two largest advertising agencies for thirteen years. The teams that created the ads have attributes. These include (1) the agencies that produced the ads and (2) the medium for which each ad was produced. There is plenty of both qualitative and quantitative data to support the proposition that during the period in question TV captured both a larger share of awards and a larger share of advertising budgets, while print advertising declined, and that this was also a period in which the largest agency in the industry also captured a larger share of awards and a larger share of budgets. While attempting to determine the relationship between components and agency or media networks, I became aware of the general problem of relating the output of network analysis algorithms to known facts about the networks in question, like those mentioned above. It turns out that with Pajek it is very simple to determine, for example, the number of creators who work on award-winning ads for two or more agencies during the same year and demonstrate that the networks&#39; giant components are only thin veils over what remains a highly stovepiped industry.  As Vlado (Vladimir Batagelej) quipped after my presentation I demonstrated that Pajek can count. But, if all I am doing is shrinking networks around extended partitions, why  not see what happens with partitions generated by valued core, Louvain, or VOS or other clustering algorithms....This anyway is the thought driving my curiosity about detailed differences in expectations concerning the output of various methods.</div>
<div style><br></div><div style>Again, thanks for your advice and the link to the Fortunato paper.</div><div style><br></div><div style>John</div></div><div class="gmail_extra"><br><br><div class="gmail_quote">On Mon, Aug 5, 2013 at 11:06 PM, Carlos Sanz Rodriguez <span dir="ltr">&lt;<a href="mailto:[log in to unmask]" target="_blank"><a href="/cgi-bin/wa?LOGON=A3%3Dind1308%26L%3DSOCNET%26E%3Dquoted-printable%26P%3D91962%26B%3D--e89a8f3bae4988694004e3344b69%26T%3Dtext%252Fhtml%3B%2520charset%3Dwindows-1252" target="_parent" >[log in to unmask]</a></a>&gt;</span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div style="word-wrap:break-word">Of course there a fundamental different between two methods. VOS is base on betweenness centrality and Louvain is base on modularity. This one difference of approaches of the problem generate two different views of your networks. Lovain has a resolution limits and this cause a problem with isolated nodes, but is very good to approximate to a modular structure of a network. VOS is a good to resolve a community structure in different level, but have the problem the many nodes with certain betweenness score are inside the community in the reality and not outside like frequently the method said, so in this case Louvain resolve better the structure than VOS in many case. The decision many times come from how well you know your data and the behavior of the your communities. In my case, a study metabolic network and almost all the time the communities correlated with some function in the metabolism, so the method hat I apply and select to my &#39;after analysis&#39;, depend on how week the algorithm describe the organization of my data and function inside the metabolism. <div>
There are a very good an extensive review of a community detection methods from Santo Fortunato: Physics Reports (2010) Vol. 46 p. 75.In this Review the VOS methods referred like &#39;Newman approach&#39;. There are many, many methods for community detection and there are not a master method, all of them have a good performance to a some networks and are very bad for others. These methods that offer Pajek are too popular and using for many people, but that are not perfect.</div>
<div>Well, I hope that you can found what method is better for you question.</div><div>Best, </div><div>Carlos</div><div><br><div><div>
<div>Carlos Sanz Rodriguez<br>Departamento de Biología Celular<br>Universidad Simón Bolívar<br>Caracas, Apartado 89000<br>Telf <a href="tel:%2B58-212-9064219" value="+582129064219" target="_blank">+58-212-9064219</a><br>
<br>Laboratorio de Dinámica Estocástica<br>Centro de Fisica, I.V.I.C.<br>Caracas, Apartado 1020-A<br>Telf <a href="tel:%2B58-212-5041919" value="+582125041919" target="_blank">+58-212-5041919</a><br></div>
</div>
<br><div><div>El 04/08/2013, a las 21:28, John McCreery &lt;<a href="mailto:[log in to unmask]" target="_blank"><a href="/cgi-bin/wa?LOGON=A3%3Dind1308%26L%3DSOCNET%26E%3Dquoted-printable%26P%3D91962%26B%3D--e89a8f3bae4988694004e3344b69%26T%3Dtext%252Fhtml%3B%2520charset%3Dwindows-1252" target="_parent" >[log in to unmask]</a></a>&gt; escribió:</div><br><blockquote type="cite"><div><div class="h5"><div dir="ltr">
Two recent runs through part of my data using the Pajek commands for, first, VOS and, second, Louvain community detection. My question is why the results using the Louvain method seem lumpier than those using the VOS method. Note, for example, that cluster 1 in the VOS distribution has 36 members, while cluster 1 using the Louvain method has 97. Using the VOS method, cluster 11 has 35 members, while cluster 11 using the Louvain method has 101. Is there a straightforward explanation why the two algorithms produce such apparently different results? Or is this just a random event?<div>

<br></div><div>Thoughts?</div><div><br></div><div>John (data follows)<br><div><br></div><div>(1)</div><div><br></div><div><div><br></div><div>==============================================================================</div>

<div>1. VOS Clustering in N1 (637, Res=1.000000, VOS=0.9010200019, NC=54)</div><div>==============================================================================</div><div>Dimension: 637</div><div>The lowest value:  1</div>

<div>The highest value: 54</div><div><br></div><div>Frequency distribution of cluster values:</div><div><br></div><div>   Cluster      Freq     Freq%   CumFreq  CumFreq% Representative</div><div> ----------------------------------------------------------------</div>

<div>         1        36    5.6515        36    5.6515 AD1_01</div><div>         2        23    3.6107        59    9.2622 AD9_01</div><div>         3        67   10.5181       126   19.7802 AD15_01</div><div>         4        30    4.7096       156   24.4898 AD25_01</div>

<div>         5        31    4.8666       187   29.3564 AD26_01</div><div>         6        42    6.5934       229   35.9498 AD30_01</div><div>         7        41    6.4364       270   42.3862 AD34_01</div><div>         8        24    3.7677       294   46.1538 AD38_01</div>

<div>         9        42    6.5934       336   52.7473 AD41_01</div><div>        10         3    0.4710       339   53.2182 AD46_01</div><div>        11        35    5.4945       374   58.7127 AD53_01</div><div>        12        19    2.9827       393   61.6954 AD61_01</div>

<div>        13        48    7.5353       441   69.2308 AD66_01</div><div>        14        37    5.8085       478   75.0392 AD70_01</div><div>        15        45    7.0644       523   82.1036 AD80_01</div><div>        16         7    1.0989       530   83.2025 AD84_01</div>

<div>        17         2    0.3140       532   83.5165 AD103_01</div><div>        18        24    3.7677       556   87.2841 AD111_01</div><div>        19         1    0.1570       557   87.4411 AD140_01</div><div>        20        13    2.0408       570   89.4819 AD143_01</div>

<div>        21         2    0.3140       572   89.7959 AD159_01</div><div>        22         1    0.1570       573   89.9529 AD170_01</div><div>        23         4    0.6279       577   90.5808 AD173_01</div><div>        24         1    0.1570       578   90.7378 AD181_01</div>

<div>        25         1    0.1570       579   90.8948 AD222_01</div><div>        26        22    3.4537       601   94.3485 AD225_01</div><div>        27         1    0.1570       602   94.5055 AD250_01</div><div>        28         3    0.4710       605   94.9765 AD289_01</div>

<div>        29         1    0.1570       606   95.1334 AD309_01</div><div>        30         1    0.1570       607   95.2904 AD316_01</div><div>        31         2    0.3140       609   95.6044 AD344_01</div><div>        32         2    0.3140       611   95.9184 AD346_01</div>

<div>        33         1    0.1570       612   96.0754 AD350_01</div><div>        34         2    0.3140       614   96.3893 AD352_01</div><div>        35         2    0.3140       616   96.7033 AD353_01</div><div>        36         1    0.1570       617   96.8603 AD354_01</div>

<div>        37         1    0.1570       618   97.0173 AD356_01</div><div>        38         1    0.1570       619   97.1743 AD389_01</div><div>        39         1    0.1570       620   97.3312 AD394_01</div><div>        40         2    0.3140       622   97.6452 AD395_01</div>

<div>        41         1    0.1570       623   97.8022 AD420_01</div><div>        42         1    0.1570       624   97.9592 AD471_01</div><div>        43         2    0.3140       626   98.2732 AD544_01</div><div>        44         1    0.1570       627   98.4301 AD546_01</div>

<div>        45         1    0.1570       628   98.5871 AD560_01</div><div>        46         1    0.1570       629   98.7441 AD564_01</div><div>        47         1    0.1570       630   98.9011 AD580_01</div><div>        48         1    0.1570       631   99.0581 AD592_01</div>

<div>        49         1    0.1570       632   99.2151 AD593_01</div><div>        50         1    0.1570       633   99.3721 AD621_01</div><div>        51         1    0.1570       634   99.5290 AD623_01</div><div>        52         1    0.1570       635   99.6860 AD624_01</div>

<div>        53         1    0.1570       636   99.8430 AD630_01</div><div>        54         1    0.1570       637  100.0000 AD634_01</div><div> ----------------------------------------------------------------</div><div>

       Sum       637  100.0000</div><div><br></div><div>(2)</div><div><br></div><div><div><br></div><div>==============================================================================</div><div>1. Louvain Communities in N4 (637, Res=1.000000, Q=0.601442, NC=53)</div>

<div>==============================================================================</div><div>Dimension: 637</div><div>The lowest value:  1</div><div>The highest value: 53</div><div><br></div><div>Frequency distribution of cluster values:</div>

<div><br></div><div>   Cluster      Freq     Freq%   CumFreq  CumFreq% Representative</div><div> ----------------------------------------------------------------</div><div>         1        97   15.2276        97   15.2276 AD1_01</div>

<div>         2        68   10.6750       165   25.9027 AD15_01</div><div>         3        48    7.5353       213   33.4380 AD25_01</div><div>         4        45    7.0644       258   40.5024 AD34_01</div><div>         5        23    3.6107       281   44.1130 AD37_01</div>

<div>         6        17    2.6688       298   46.7818 AD38_01</div><div>         7         3    0.4710       301   47.2527 AD46_01</div><div>         8        58    9.1052       359   56.3579 AD50_01</div><div>         9        33    5.1805       392   61.5385 AD53_01</div>

<div>        10        11    1.7268       403   63.2653 AD61_01</div><div>        11       101   15.8556       504   79.1209 AD66_01</div><div>        12         7    1.0989       511   80.2198 AD84_01</div><div>        13         2    0.3140       513   80.5338 AD103_01</div>

<div>        14        14    2.1978       527   82.7316 AD110_01</div><div>        15        25    3.9246       552   86.6562 AD111_01</div><div>        16        28    4.3956       580   91.0518 AD123_01</div><div>        17         1    0.1570       581   91.2088 AD140_01</div>

<div>        18         2    0.3140       583   91.5228 AD159_01</div><div>        19         1    0.1570       584   91.6797 AD170_01</div><div>        20         4    0.6279       588   92.3077 AD173_01</div><div>        21         1    0.1570       589   92.4647 AD181_01</div>

<div>        22         1    0.1570       590   92.6217 AD222_01</div><div>        23         4    0.6279       594   93.2496 AD224_01</div><div>        24         1    0.1570       595   93.4066 AD250_01</div><div>        25         3    0.4710       598   93.8776 AD289_01</div>

<div>        26         1    0.1570       599   94.0345 AD309_01</div><div>        27         1    0.1570       600   94.1915 AD316_01</div><div>        28         3    0.4710       603   94.6625 AD322_01</div><div>        29         2    0.3140       605   94.9765 AD344_01</div>

<div>        30         1    0.1570       606   95.1334 AD350_01</div><div>        31         2    0.3140       608   95.4474 AD352_01</div><div>        32         2    0.3140       610   95.7614 AD353_01</div><div>        33         1    0.1570       611   95.9184 AD354_01</div>

<div>        34         1    0.1570       612   96.0754 AD356_01</div><div>        35         1    0.1570       613   96.2323 AD389_01</div><div>        36         1    0.1570       614   96.3893 AD394_01</div><div>        37         2    0.3140       616   96.7033 AD395_01</div>

<div>        38         1    0.1570       617   96.8603 AD420_01</div><div>        39         2    0.3140       619   97.1743 AD447_01</div><div>        40         4    0.6279       623   97.8022 AD462_01</div><div>        41         1    0.1570       624   97.9592 AD471_01</div>

<div>        42         2    0.3140       626   98.2732 AD544_01</div><div>        43         1    0.1570       627   98.4301 AD546_01</div><div>        44         1    0.1570       628   98.5871 AD560_01</div><div>        45         1    0.1570       629   98.7441 AD564_01</div>

<div>        46         1    0.1570       630   98.9011 AD580_01</div><div>        47         1    0.1570       631   99.0581 AD592_01</div><div>        48         1    0.1570       632   99.2151 AD593_01</div><div>        49         1    0.1570       633   99.3721 AD621_01</div>

<div>        50         1    0.1570       634   99.5290 AD623_01</div><div>        51         1    0.1570       635   99.6860 AD624_01</div><div>        52         1    0.1570       636   99.8430 AD630_01</div><div>        53         1    0.1570       637  100.0000 AD634_01</div>

<div> ----------------------------------------------------------------</div><div>       Sum       637  100.0000</div></div><div><br></div>-- <br>John McCreery<br>The Word Works, Ltd., Yokohama, JAPAN<br>Tel. <a href="tel:%2B81-45-314-9324" value="+81453149324" target="_blank">+81-45-314-9324</a><br>

<a href="mailto:[log in to unmask]" target="_blank"><a href="/cgi-bin/wa?LOGON=A3%3Dind1308%26L%3DSOCNET%26E%3Dquoted-printable%26P%3D91962%26B%3D--e89a8f3bae4988694004e3344b69%26T%3Dtext%252Fhtml%3B%2520charset%3Dwindows-1252" target="_parent" >[log in to unmask]</a></a><br><a href="http://www.wordworks.jp/" target="_blank">http://www.wordworks.jp/</a>
</div></div></div></div></div><div class="im">
_______________________________________________<br>Pajek mailing list<br><a href="mailto:[log in to unmask]" target="_blank"><a href="/cgi-bin/wa?LOGON=A3%3Dind1308%26L%3DSOCNET%26E%3Dquoted-printable%26P%3D91962%26B%3D--e89a8f3bae4988694004e3344b69%26T%3Dtext%252Fhtml%3B%2520charset%3Dwindows-1252" target="_parent" >[log in to unmask]</a></a><br><a href="http://list.fmf.uni-lj.si/cgi-bin/mailman/listinfo/pajek" target="_blank">http://list.fmf.uni-lj.si/cgi-bin/mailman/listinfo/pajek</a><br>
</div></blockquote></div><br></div></div></div></blockquote></div><br><br clear="all"><div><br></div>-- <br>John McCreery<br>The Word Works, Ltd., Yokohama, JAPAN<br>Tel. +81-45-314-9324<br><a href="mailto:[log in to unmask]"><a href="/cgi-bin/wa?LOGON=A3%3Dind1308%26L%3DSOCNET%26E%3Dquoted-printable%26P%3D91962%26B%3D--e89a8f3bae4988694004e3344b69%26T%3Dtext%252Fhtml%3B%2520charset%3Dwindows-1252" target="_parent" >[log in to unmask]</a></a><br>
<a href="http://www.wordworks.jp/">http://www.wordworks.jp/</a>
</div>
_____________________________________________________________________
SOCNET is a service of INSNA, the professional association for social
network researchers (http://www.insna.org). To unsubscribe, send
an email message to <a href="/cgi-bin/wa?LOGON=A3%3Dind1308%26L%3DSOCNET%26E%3Dquoted-printable%26P%3D91962%26B%3D--e89a8f3bae4988694004e3344b69%26T%3Dtext%252Fhtml%3B%2520charset%3Dwindows-1252" target="_parent" >[log in to unmask]</a> containing the line
UNSUBSCRIBE SOCNET in the body of the message.