<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Archiving and Interchange DTD v1.0 20120330//EN" "JATS-archivearticle1.dtd">
<article xmlns:xlink="http://www.w3.org/1999/xlink">
  <front>
    <journal-meta />
    <article-meta />
  </front>
  <body>
    <sec id="sec-1">
      <title>-</title>
      <p>E
U</p>
      <p>R
W
o
r
k
s
h
o
p
P
r
o
c
e
e
d
i
n
g
s
c
e
u
r
LGOBE
Distribution of each frame label (main media frame) in the Gun Violence Frame Corpus [9].
38
215
373
65
137
114
237
41
80
”Breaking down the 27 words of the Second Amendment“
”How gun background checks work“
”Romney open to new gun measures“
”Florida shooter a troubled loner with white supremacist ties“
7 ways to help prevent school shootings
”Lawyers call US gun charges for Mexican man ’vindictive’“
“Students call for action after Florida school mass shooting”
“White House weighs video game link to gun violence”
“Calstrs to engage with assault-weapon sellers first, divest last”</p>
      <p>Technical methodological diagram illustrating the key steps in the narrative extraction and
analysis process, starting with the preprocessed final data set and ending with the quantitative and
qualitative evaluation of the resulting narrative maps.</p>
    </sec>
    <sec id="sec-2">
      <title>Chain Constraints</title>
    </sec>
    <sec id="sec-3">
      <title>Clustering</title>
      <p>
        Linear programming formulation of the extraction method of Keith and Mitra [
        <xref ref-type="bibr" rid="ref2">3</xref>
        ].
 = 6
Map sizes of each combination starting and ending frames based on number of events in the map.
      </p>
      <sec id="sec-3-1">
        <title>Start: Frame 1</title>
        <p>Start: Frame 2
Start: Frame 3
Jensen-Shannon divergence values obtained by comparing the framing distribution of each combination
starting and ending frames with the distribution of the data set.</p>
      </sec>
      <sec id="sec-3-2">
        <title>Start: Frame 1 Start: Frame 2 Start: Frame 3</title>
        <p>Average</p>
        <p>Sample narrative map extracted from news events spanning January to June 2018. Events are
represented as nodes labeled with headlines and frames. Connections indicate narrative relationships
between events. Inconsistencies in framing across the map highlight challenges in producing coherent
framing narratives through the extraction process.</p>
        <p>1145/3584741</p>
      </sec>
    </sec>
  </body>
  <back>
    <ref-list>
      <ref id="ref1">
        <mixed-citation>
          <volume>1</volume>
          : 2nd Amendment [
          <volume>18</volume>
          ] 2:
          <string-name>
            <given-names>Gun</given-names>
            <surname>Control</surname>
          </string-name>
          /Regulation [18]
        </mixed-citation>
      </ref>
      <ref id="ref2">
        <mixed-citation>3: Politics [19]</mixed-citation>
      </ref>
      <ref id="ref3">
        <mixed-citation>
          4:
          <string-name>
            <given-names>Mental</given-names>
            <surname>Health</surname>
          </string-name>
          [
          <volume>20</volume>
          ] 5: School/Public Space Safety [
          <volume>21</volume>
          ]
        </mixed-citation>
      </ref>
      <ref id="ref4">
        <mixed-citation>6: Race/Ethnicity [22]</mixed-citation>
      </ref>
      <ref id="ref5">
        <mixed-citation>
          7:
          <string-name>
            <given-names>Public</given-names>
            <surname>Opinion</surname>
          </string-name>
          [
          <volume>23</volume>
          ]
        </mixed-citation>
      </ref>
      <ref id="ref6">
        <mixed-citation>
          8: Society/Culture [24] 9:
          <string-name>
            <given-names>Economic</given-names>
            <surname>Consequences</surname>
          </string-name>
          [
          <volume>23</volume>
          ]
        </mixed-citation>
      </ref>
    </ref-list>
  </back>
</article>