BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.cienciaenmexico.com//igisc-2026//talk//Y3MVK7
BEGIN:VTIMEZONE
TZID:CST
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=5SU;BYMONTH=10;UNTIL=20001029T080000Z
TZNAME:CST
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
END:STANDARD
BEGIN:STANDARD
DTSTART:20010930T030000
RRULE:FREQ=YEARLY;BYDAY=5SU;BYMONTH=9;UNTIL=20010930T080000Z
TZNAME:CST
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
END:STANDARD
BEGIN:STANDARD
DTSTART:20021027T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CST
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000402T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4;UNTIL=20000402T090000Z
TZNAME:CDT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20010506T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=5;UNTIL=20010506T090000Z
TZNAME:CDT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20020407T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4;UNTIL=20220403T090000Z
TZNAME:CDT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-igisc-2026-Y3MVK7@pretalx.cienciaenmexico.com
DTSTART;TZID=CST:20261111T120000
DTEND;TZID=CST:20261111T121500
DESCRIPTION:## Introduction\nToday\, digital media produce large volumes of
  information on a daily basis that document social\, political\, environme
 ntal\, and economic events\, among others. Within these texts\, it is comm
 on to find numerous references to geographic locations that help contextua
 lize and spatially understand the events described. However\, most of thes
 e references are merely part of a text\, which makes it difficult to integ
 rate them with geographic analysis tools and to study spatial patterns der
 ived from journalistic discourse. The point is that what matters is not on
 ly extracting these geographic references but also being able to assess wh
 ether they are relevant to the subject of study. Today\, digital media pro
 duce large volumes of information daily that document social\, political\,
  environmental\, economic\, and other events. Within these texts\, it is c
 ommon to find numerous references to geographic locations that allow us to
  contextualize and spatially understand the events described. However\, mo
 st of these references are merely part of a text\, which makes it difficul
 t to integrate them with geographic analysis tools and to study spatial pa
 tterns derived from journalistic discourse. The key is not only to extract
  these geographic references but also to be able to assess whether they ar
 e relevant to the subject under study.\nThis paper presents a methodology 
 for automatically converting geographic references found in news articles 
 into geospatial information. Not only that\, but it also allows us to meas
 ure the relevance of these locations so that we can generate maps more acc
 urately and precisely\, filtering and selecting the locations most relevan
 t to our study while discarding those that are not. This proposal integrat
 es various stages of automated processing\, ranging from extracting geogra
 phic coordinates from textual documents and measuring the relevance of eac
 h location to generating cartographic products that can be further analyze
 d using Geographic Information Systems.\n## Geocentrality Metric\nGeocentr
 ality is a LexRank-based metric that measures the degree of importance of 
 a geographic area in relation to a document’s topic. This metric is not 
 merely equivalent to the presence of place names. A document may mention c
 ountries or regions without these having any analytical significance.\nTo 
 define this metric\, we must first define the geocentrality of a place nam
 e.\nFor a place name $t$ and a document $D$\, we define the geocentrality 
 metric as a function of $t$ and $D$ according to Equation (1).\nWhere $s_i
 $ are the sentences in document $D$\, and $c(s_i)$ is a function that scor
 es the importance of sentence $s_i$.\n\n$$\\text{geocentrality}(t\, D) = \
 \frac{\\sum_{i : s_i \\ni t} c(s_i)}{\\sum_i c(s_i)} \\tag{1}$$\n\nThus\, 
 we can define the geocentrality of document $D$ simply as the average geoc
 entrality of all its geographic entities\, or as zero if it does not menti
 on any place names (Equation 2).\n\n$$\\text{average\\_geocentrality}(D) =
  \\begin{cases} \\frac{1}{n}\\sum_{i=1}^{n} \\text{geocentrality}(t_i\, D)
 \, & \\text{if } n>0 \\\\ 0\, & \\text{if } n=0 \\end{cases} \\tag{2}$$\n\
 nAt the corpus level\, we define the geocentrality of $t$ in a $corpus$ ac
 cording to Equation (3).\n\n$$\\text{corpus\\_geocentrality}(t) = \\frac{\
 \sum_{D} \\sum_{i: s_i \\ni t} c(s_i)}{\\sum_{D} \\sum_{i} c(s_i)} \\tag{3
 }$$\n\n## Metodology \nThe methodology begins with the collection of news 
 articles using web crawling techniques. The documents obtained are stored 
 in a structured database that preserves both the textual content and suppl
 ementary information\, such as the publication date\, the news outlet\, an
 d other relevant data.\nNext\, the text undergoes preprocessing to prepare
  the information for analysis. During this stage\, the text is segmented i
 nto sentences\, the content is normalized\, and named entities are automat
 ically extracted using Named Entity Recognition (NER) techniques. This pro
 cess primarily identifies people\, organizations\, and places\, with the l
 atter serving as the main input for the georeferencing process.\nDue to th
 e nature of language in general\, the entities that are identified often h
 ave spelling variations\, abbreviations\, incomplete names\, or synonyms t
 hat refer to the same place. Therefore\, the methodology includes a standa
 rdization process that seeks to unify these variations before performing g
 eocoding. This stage significantly improves the consistency of the results
  and reduces the number of queries during the geoparsing process.\nOnce th
 e geographic entities have been standardized\, a geoparsing procedure is a
 pplied that combines textual information with geocoding services. For this
  purpose\, Nominatim was used\, which allows querying the OpenStreetMap op
 en database to obtain the possible standardized address\, as well as the g
 eographic coordinates corresponding to each identified entity. It is impor
 tant to note that this process also incorporated a spatial constraint tail
 ored to the context of the study\, reducing ambiguity in cases where multi
 ple locations share the same name.\nThe result of this stage is a set of g
 eographic entities with spatial information that can be visualized directl
 y on maps or incorporated into geographic analysis tools.\nAs a case study
 \, this methodology is applied to the analysis of journalistic discourse r
 elated to the socio-environmental conflict over water in the state of Jali
 sco\, Mexico\, in the year 2024. A corpus consisting of news articles from
  three media outlets is used: El Mural\, El Informador\, and La Jornada. T
 he objective is not only to identify geographic entities but also to analy
 ze the spatial distribution of the places mentioned in journalistic discou
 rse and to explore how different media outlets represent this phenomenon t
 erritorially.\nIn addition to spatial analysis\, the proposed methodology 
 incorporates the geocentrality metric to estimate the relevance of geograp
 hic entities within each media outlet. \n## Conclusion\nUnlike traditional
  approaches\, which typically treat all identified locations equally\, geo
 centrality allows us to classify geographic entities based on their semant
 ic importance within the document\, enabling the creation of thematic maps
  that highlight the locations most relevant to the topic under study. This
  approach\, combined with the extraction of geographic entities and the ac
 quisition of spatial data\, can facilitate a spatial interpretation of jou
 rnalistic discourse\, as this methodology highlights the geographic areas 
 that play a central role in the events under analysis.
DTSTAMP:20261122T124240Z
LOCATION:Video Room
SUMMARY:From Text to Map: A Methodology for the Automatic Georeferencing of
  Geographic Entities Extracted from News Articles and Their Relevance in D
 iscourse. - Manuel Morales Almora
URL:https://pretalx.cienciaenmexico.com/igisc-2026/talk/Y3MVK7/
END:VEVENT
END:VCALENDAR
