Social Media, Topic Modeling and Sentiment Analysis in Municipal Decision Support
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27510%2F23%3A10253055" target="_blank" >RIV/61989100:27510/23:10253055 - isvavai.cz</a>
Výsledek na webu
<a href="https://annals-csis.org/proceedings/2023/drp/1479.html" target="_blank" >https://annals-csis.org/proceedings/2023/drp/1479.html</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.15439/2023F1479" target="_blank" >10.15439/2023F1479</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Social Media, Topic Modeling and Sentiment Analysis in Municipal Decision Support
Popis výsledku v původním jazyce
Many cities around the world are aspiring to become smart. However, smart initiatives often give little weight to the opinions of average citizens. One reason is the difficulty and high cost of opinion collection process. Social media are one of many sources of citizen opinions. This paper presents a prototype of a framework for processing social media posts with municipal decision-making in mind. The framework consists of a sequence of three steps: (1) determining the sentiment polarity of each social media post (2) extracting topics being discussed in a set of social media posts and creating a mapping between identified topics and individual posts, and (3) aggregating these two pieces of information into a triangular fuzzy number representing the overall sentiment expressed to- wards each topic. Optionally, the triangular fuzzy number can be reduced into a tuple of two real numbers indicating the "amount" of positive and negative opinion expressed towards each topic. Framework functionality is demonstrated on tweets published from Ostrava, Czechia over a period of about two months. This application illustrates that the resulting TFNs represent sentiment in a richer way, also capturing the diversity or controversy of opinions expressed on social media.
Název v anglickém jazyce
Social Media, Topic Modeling and Sentiment Analysis in Municipal Decision Support
Popis výsledku anglicky
Many cities around the world are aspiring to become smart. However, smart initiatives often give little weight to the opinions of average citizens. One reason is the difficulty and high cost of opinion collection process. Social media are one of many sources of citizen opinions. This paper presents a prototype of a framework for processing social media posts with municipal decision-making in mind. The framework consists of a sequence of three steps: (1) determining the sentiment polarity of each social media post (2) extracting topics being discussed in a set of social media posts and creating a mapping between identified topics and individual posts, and (3) aggregating these two pieces of information into a triangular fuzzy number representing the overall sentiment expressed to- wards each topic. Optionally, the triangular fuzzy number can be reduced into a tuple of two real numbers indicating the "amount" of positive and negative opinion expressed towards each topic. Framework functionality is demonstrated on tweets published from Ostrava, Czechia over a period of about two months. This application illustrates that the resulting TFNs represent sentiment in a richer way, also capturing the diversity or controversy of opinions expressed on social media.
Klasifikace
Druh
D - Stať ve sborníku
CEP obor
—
OECD FORD obor
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Návaznosti výsledku
Projekt
—
Návaznosti
S - Specificky vyzkum na vysokych skolach
Ostatní
Rok uplatnění
2023
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název statě ve sborníku
Proceedings of the 18th Conference on Computer Science and Intelligence Systems : September 17–20, 2023, Warsaw, Poland
ISBN
978-83-967447-8-4
ISSN
2300-5963
e-ISSN
2300-5963
Počet stran výsledku
5
Strana od-do
1235-1239
Název nakladatele
Polskie Towarzystwo Informatyczne
Místo vydání
Varšava
Místo konání akce
Varšava
Datum konání akce
17. 9. 2023
Typ akce podle státní příslušnosti
WRD - Celosvětová akce
Kód UT WoS článku
—