Geo-spatial-based emotions: A mechanism for event detection in microblogs

Samer Muthana Sarsam; Hosam Al-Samarraie; Bahiyah Omar

doi:10.1145/3316615.3316640

Geo-spatial-based emotions: A mechanism for event detection in microblogs

Samer Muthana Sarsam, Hosam Al-Samarraie, Bahiyah Omar

Universiti Sains Malaysia

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding › peer-review

5 Citations (Scopus)

Abstract

The use of emotions in microblogs to trace the occurrence of certain events and determine their locations is an open challenge for sentiment analysis. This study investigated the potential of detecting the geographical location of events based on existing linkages between the types of emotion embedded in tweets (degree of polarity) and the source location of those tweets. The extracted tweets were clustered using K-means algorithm and a predictive model was developed using Naïve Bayes algorithm. Then, a time series forecasting technique was applied using linear regression analysis. This method was used to predict the amount of emotions in association with the event of interest. Latitude and longitude were used to evaluate the results of the linear regression model on a real-time world map. Results showed that happy emotion tends to be a reliable source for detecting the geographical location of an event. This study revealed the feasibility of using the time series forecasting approach in investigating the degree of emotions in twitter messages.

Original language	English
Title of host publication	ICSCA '19 Proceedings of the 2019 8th International Conference on Software and Computer Applications
Publisher	ACM
Pages	1-5
Number of pages	5
ISBN (Print)	978-1-4503-6573-4
DOIs	https://doi.org/10.1145/3316615.3316640
Publication status	Published - 2019
Externally published	Yes
Event	8th International Conference on Software and Computer Applications - Penang, Malaysia Duration: 19 Feb 2019 → 21 Feb 2019 http://www.icsca.org/

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	8th International Conference on Software and Computer Applications
Abbreviated title	ICSCA 2019
Country/Territory	Malaysia
City	Penang
Period	19/02/19 → 21/02/19
Internet address	http://www.icsca.org/

Keywords

Microblogs
Polarity
Sentiment analysis
Time series forecasting

ASJC Scopus subject areas

Human-Computer Interaction
Computer Networks and Communications
Computer Vision and Pattern Recognition
Software

Access to Document

10.1145/3316615.3316640

Cite this

Geo-spatial-based emotions: A mechanism for event detection in microblogs. / Sarsam, Samer Muthana; Al-Samarraie, Hosam; Omar, Bahiyah.
ICSCA '19 Proceedings of the 2019 8th International Conference on Software and Computer Applications. ACM, 2019. p. 1-5 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding › peer-review

Sarsam, SM, Al-Samarraie, H & Omar, B 2019, Geo-spatial-based emotions: A mechanism for event detection in microblogs. in ICSCA '19 Proceedings of the 2019 8th International Conference on Software and Computer Applications. ACM International Conference Proceeding Series, ACM, pp. 1-5, 8th International Conference on Software and Computer Applications, Penang, Malaysia, 19/02/19. https://doi.org/10.1145/3316615.3316640

@inproceedings{1b566a0f419447528eacced1cf0760aa,

title = "Geo-spatial-based emotions: A mechanism for event detection in microblogs",

abstract = "The use of emotions in microblogs to trace the occurrence of certain events and determine their locations is an open challenge for sentiment analysis. This study investigated the potential of detecting the geographical location of events based on existing linkages between the types of emotion embedded in tweets (degree of polarity) and the source location of those tweets. The extracted tweets were clustered using K-means algorithm and a predictive model was developed using Na{\"i}ve Bayes algorithm. Then, a time series forecasting technique was applied using linear regression analysis. This method was used to predict the amount of emotions in association with the event of interest. Latitude and longitude were used to evaluate the results of the linear regression model on a real-time world map. Results showed that happy emotion tends to be a reliable source for detecting the geographical location of an event. This study revealed the feasibility of using the time series forecasting approach in investigating the degree of emotions in twitter messages.",

keywords = "Microblogs, Polarity, Sentiment analysis, Time series forecasting",

author = "Sarsam, {Samer Muthana} and Hosam Al-Samarraie and Bahiyah Omar",

year = "2019",

doi = "10.1145/3316615.3316640",

language = "English",

isbn = "978-1-4503-6573-4",

series = "ACM International Conference Proceeding Series",

publisher = "ACM",

pages = "1--5",

booktitle = "ICSCA '19 Proceedings of the 2019 8th International Conference on Software and Computer Applications",

address = "United States",

note = "8th International Conference on Software and Computer Applications, ICSCA 2019 ; Conference date: 19-02-2019 Through 21-02-2019",

url = "http://www.icsca.org/",

}

TY - GEN

T1 - Geo-spatial-based emotions

T2 - 8th International Conference on Software and Computer Applications

AU - Sarsam, Samer Muthana

AU - Al-Samarraie, Hosam

AU - Omar, Bahiyah

PY - 2019

Y1 - 2019

N2 - The use of emotions in microblogs to trace the occurrence of certain events and determine their locations is an open challenge for sentiment analysis. This study investigated the potential of detecting the geographical location of events based on existing linkages between the types of emotion embedded in tweets (degree of polarity) and the source location of those tweets. The extracted tweets were clustered using K-means algorithm and a predictive model was developed using Naïve Bayes algorithm. Then, a time series forecasting technique was applied using linear regression analysis. This method was used to predict the amount of emotions in association with the event of interest. Latitude and longitude were used to evaluate the results of the linear regression model on a real-time world map. Results showed that happy emotion tends to be a reliable source for detecting the geographical location of an event. This study revealed the feasibility of using the time series forecasting approach in investigating the degree of emotions in twitter messages.

AB - The use of emotions in microblogs to trace the occurrence of certain events and determine their locations is an open challenge for sentiment analysis. This study investigated the potential of detecting the geographical location of events based on existing linkages between the types of emotion embedded in tweets (degree of polarity) and the source location of those tweets. The extracted tweets were clustered using K-means algorithm and a predictive model was developed using Naïve Bayes algorithm. Then, a time series forecasting technique was applied using linear regression analysis. This method was used to predict the amount of emotions in association with the event of interest. Latitude and longitude were used to evaluate the results of the linear regression model on a real-time world map. Results showed that happy emotion tends to be a reliable source for detecting the geographical location of an event. This study revealed the feasibility of using the time series forecasting approach in investigating the degree of emotions in twitter messages.

KW - Microblogs

KW - Polarity

KW - Sentiment analysis

KW - Time series forecasting

UR - http://www.scopus.com/inward/record.url?scp=85066036206&partnerID=8YFLogxK

U2 - 10.1145/3316615.3316640

DO - 10.1145/3316615.3316640

M3 - Conference proceeding

AN - SCOPUS:85066036206

SN - 978-1-4503-6573-4

T3 - ACM International Conference Proceeding Series

SP - 1

EP - 5

BT - ICSCA '19 Proceedings of the 2019 8th International Conference on Software and Computer Applications

PB - ACM

Y2 - 19 February 2019 through 21 February 2019

ER -

Geo-spatial-based emotions: A mechanism for event detection in microblogs

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this