use footnotes for some of the references

web-archive-group · Jun 23, 2017 · 22ae65e · 22ae65e
1 parent 157c744
commit 22ae65e
Show file tree

Hide file tree

Showing 5 changed files with 21 additions and 53 deletions.
diff --git a/... for Collecting, Processing, and Analyzing Tweets from Large Newsworthy Events/paper7.aux b/... for Collecting, Processing, and Analyzing Tweets from Large Newsworthy Events/paper7.aux
@@ -17,19 +17,13 @@
 \providecommand\HyField@AuxAddToFields[1]{}
 \providecommand\HyField@AuxAddToCoFields[2]{}
 \citation{Milligan_etal_JCDL2016}
-\citation{twitter_filter}
-\citation{twitter_search}
 \citation{Driscoll_etal_IJC2014}
-\citation{summers_twarc_2015}
 \citation{ruest_2016}
 \bibstyle{ACM-Reference-Format}
 \bibdata{paper7}
 \bibcite{Driscoll_etal_IJC2014}{{1}{2014}{{Driscoll and Walker}}{{Driscoll and Walker}}}
 \bibcite{Milligan_etal_JCDL2016}{{2}{2016}{{Milligan et~al\unhbox \voidb@x \hbox {.}}}{{Milligan, Ruest, and Lin}}}
 \bibcite{ruest_2016}{{3}{2016}{{Ruest}}{{Ruest}}}
-\bibcite{summers_twarc_2015}{{4}{2017}{{Summers et~al\unhbox \voidb@x \hbox {.}}}{{Summers, van Kemenadem, Binkley, Ruest, recrm, Costa, Phetteplace, Badger, Matienzo, Blakk, Chudnov, and Nelson}}}
-\bibcite{twitter_filter}{{5}{[n. d.]a}{{Twitter}}{{Twitter}}}
-\bibcite{twitter_search}{{6}{[n. d.]b}{{Twitter}}{{Twitter}}}
 \newlabel{tocindent-1}{0pt}
 \newlabel{tocindent0}{0pt}
 \newlabel{tocindent1}{4.185pt}

diff --git a/... for Collecting, Processing, and Analyzing Tweets from Large Newsworthy Events/paper7.bib b/... for Collecting, Processing, and Analyzing Tweets from Large Newsworthy Events/paper7.bib
@@ -25,42 +25,10 @@ @article{Driscoll_etal_IJC2014
    year = 2014,
 }
 
-@misc{summers_twarc_2015,
-  author       = {Summers, Ed and
-                  van Kemenadem, Hugo and
-                  Binkley, Peter and
-                  Ruest, Nick and
-                  recrm and
-                  Costa, Stefano and
-                  Phetteplace, Eric and
-                  The Gitter Badger and
-                  Matienzo, Mx. A and
-                  Blakk, Lukas and
-                  Chudnov, Dan and
-                  Nelson, Chad},
-  title        = {twarc},
-  year         = {2013--2017},
-  url          = {http://github.com/docnow/twarc}
-}
-
 @misc{ruest_2016,
   author = "Nick Ruest",
 	title = "1,203,867 \#elxn42 images",
   month = mar,
   year = 2016,
   url = {http://ruebot.net/post/1203867-elxn42-images}
 }
-
-@misc{twitter_search,
-  author = "Twitter",
-  title = "The Search API",
-  url = {https://dev.twitter.com/rest/public/search},
-  urldate = {2017}
-} 
-
-@misc{twitter_filter,
-  author = "Twitter",
-  title = "Public Streams",
-  url = {https://dev.twitter.com/streaming/public},
-  urldate = {2017}
-}
diff --git a/... for Collecting, Processing, and Analyzing Tweets from Large Newsworthy Events/paper7.log b/... for Collecting, Processing, and Analyzing Tweets from Large Newsworthy Events/paper7.log
@@ -1,4 +1,4 @@
-This is pdfTeX, Version 3.14159265-2.6-1.40.16 (TeX Live 2015/Debian) (preloaded format=pdflatex 2017.6.22)  22 JUN 2017 15:33
+This is pdfTeX, Version 3.14159265-2.6-1.40.16 (TeX Live 2015/Debian) (preloaded format=pdflatex 2017.6.22)  23 JUN 2017 08:57
 entering extended mode
  restricted \write18 enabled.
  %&-line parsing enabled.
@@ -953,6 +953,12 @@ Underfull \hbox (badness 10000) in paragraph at lines 45--46
 
  []
 
+LaTeX Font Info:    Font shape `OT1/LinuxLibertineT-TLF/m/n' will be
+(Font)              scaled to size 9.0pt on input line 47.
+LaTeX Font Info:    Font shape `T1/LinuxLibertineT-TLF/m/n' will be
+(Font)              scaled to size 7.3pt on input line 47.
+LaTeX Font Info:    Font shape `T1/LinuxLibertineT-TLF/m/n' will be
+(Font)              scaled to size 5.5pt on input line 47.
 
 Underfull \hbox (badness 10000) in paragraph at lines 47--48
 
@@ -987,13 +993,13 @@ Package rerunfilecheck Info: File `paper7.out' has not changed.
 Package atveryend Info: Empty hook `AtVeryVeryEnd' on input line 58.
  ) 
 Here is how much of TeX's memory you used:
- 17134 strings out of 493029
- 257255 string characters out of 6136234
- 368364 words of memory out of 5000000
- 20089 multiletter control sequences out of 15000+600000
- 104151 words of font info for 158 fonts, out of 8000000 for 9000
+ 17161 strings out of 493029
+ 257768 string characters out of 6136234
+ 369364 words of memory out of 5000000
+ 20107 multiletter control sequences out of 15000+600000
+ 119035 words of font info for 172 fonts, out of 8000000 for 9000
  1302 hyphenation exceptions out of 8191
- 60i,11n,94p,673b,466s stack positions out of 5000i,500n,10000p,200000b,80000s
+ 60i,11n,94p,753b,466s stack positions out of 5000i,500n,10000p,200000b,80000s
 {/usr/share/texlive/texmf-dist/fonts/enc/dvips/libertine/lbtn_naooyc.enc}{/us
 r/share/texlive/texmf-dist/fonts/enc/dvips/libertine/lbtn_7grukw.enc}{/usr/shar
 e/texlive/texmf-dist/fonts/enc/dvips/libertine/lbtn_nh77jq.enc}{/usr/share/texl
@@ -1003,10 +1009,10 @@ st/fonts/type1/public/libertine/LinBiolinumTB.pfb></usr/share/texlive/texmf-dis
 t/fonts/type1/public/libertine/LinLibertineT.pfb></usr/share/texlive/texmf-dist
 /fonts/type1/public/libertine/LinLibertineTB.pfb></usr/share/texlive/texmf-dist
 /fonts/type1/public/libertine/LinLibertineTI.pfb>
-Output written on paper7.pdf (1 page, 292767 bytes).
+Output written on paper7.pdf (1 page, 292060 bytes).
 PDF statistics:
- 75 PDF objects out of 1000 (max. 8388607)
- 58 compressed objects within 1 object stream
- 9 named destinations out of 1000 (max. 500000)
- 34329 words of extra memory for PDF output out of 35830 (max. 10000000)
+ 72 PDF objects out of 1000 (max. 8388607)
+ 55 compressed objects within 1 object stream
+ 10 named destinations out of 1000 (max. 500000)
+ 37401 words of extra memory for PDF output out of 42996 (max. 10000000)
 
diff --git a/... for Collecting, Processing, and Analyzing Tweets from Large Newsworthy Events/paper7.pdf b/... for Collecting, Processing, and Analyzing Tweets from Large Newsworthy Events/paper7.pdf
diff --git a/... for Collecting, Processing, and Analyzing Tweets from Large Newsworthy Events/paper7.tex b/... for Collecting, Processing, and Analyzing Tweets from Large Newsworthy Events/paper7.tex
@@ -44,11 +44,11 @@
 
 \#WomensMarch, \#Aleppo, \#paris, \#bataclan, \#parisattacks, \#porteouverte, \#jesuischarlie, \#jesuisahmed, \#jesuisjuif, \#charliehebdo, \#panamanpapers, and \#exln42 are all different hashtags, but they share several things in common. They are all large newsworthy events. They are datasets that each contain over a million tweets. Most importantly these collections raise some interesting insights in collecting, processing, and analyzing large newsworthy events\cite{Milligan_etal_JCDL2016}.\\
 
-Collecting tweets from these events can be challenging because of timing. Tweets can be collected from the Filter API\cite{twitter_filter} and Search API\cite{twitter_search}. Both having their own caveats. The Filter API only captures the current Twitter stream, and is limited to collecting up to 1\% of the overall Twitter stream. The Search API allows you to collect more than 1\% of the overall Twitter stream\cite{Driscoll_etal_IJC2014}, but one can only collect up to 18,000 every 15 minutes, and is limited to a 7 day window. Generally, using a strategy of using the Filter and Search API to capture a given event is the best.\\
+Collecting tweets from these events can be challenging because of timing. Tweets can be collected from the Filter API\footnote{https://dev.twitter.com/streaming/public} and Search API\footnote{https://dev.twitter.com/rest/public/search}. Both having their own caveats. The Filter API only captures the current Twitter stream, and is limited to collecting up to 1\% of the overall Twitter stream. The Search API allows you to collect more than 1\% of the overall Twitter stream\cite{Driscoll_etal_IJC2014}, but one can only collect up to 18,000 every 15 minutes, and is limited to a 7 day window. Generally, using a strategy of using the Filter and Search API to capture a given event is the best.\\
 
-DocNow's twarc\cite{summers_twarc_2015} includes a number of utilities to process a dataset after collection. These tools allow a researcher, librarian, or archivist to filter their dataset(s) down to what is needed for appraisal, and then accession. Noteworthy tools include; deduplication, source, retweets, date/times, users, and hashtags.\\
+DocNow's twarc\footnote{http://github.com/docnow/twarc} includes a number of utilities to process a dataset after collection. These tools allow a researcher, librarian, or archivist to filter their dataset(s) down to what is needed for appraisal, and then accession. Noteworthy tools include; deduplication, source, retweets, date/times, users, and hashtags.\\
 
-DocNow's utilities can be further used to curate related collections. One can extract all the urls of a dataset, unshorten them, and extract the unique urls to use as a seed list for a web crawler to capture websites related to a given event. One can also extract all of the image urls, and download all images associated with a dataset, which then can be used for image analysis\cite{ruest_2016}, presentation, and/or preservation.\\
+DocNow's utilities\footnote{https://github.com/DocNow/twarc/tree/master/utils} can be further used to curate related collections. One can extract all the urls of a dataset, unshorten them, and extract the unique urls to use as a seed list for a web crawler to capture websites related to a given event. One can also extract all of the image urls, and download all images associated with a dataset, which then can be used for image analysis\cite{ruest_2016}, presentation, and/or preservation.\\
 
 In conclusion, this presentation will provide an overview of collection strategy, insights from processing and analysis, ensuing web crawls, and image presentation from each collection.\\