Design and implementation of natural language processing with syntax and semantic analysis for extract traffic conditions from social media data

Aziz, Mochamad Vicky Ghani; Prihatmanto, Ary Setijadi; Henriyan, Diotra; Wijaya, Rifki

doi:10.1109/icsengt.2015.7412443

Cited by 12 publications

(7 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reward mostly takes place within the groups and not externally as the authors suggested. On the other hand, [1] argued that social media data, like tweets, could not be used directly to explain road traffic condition due to their unstructured nature and raw language used. They argued that such data would be difficult to process using a computer and recommended a natural language processing approach to summarize traffic information from Twitter before disseminating to the users.…”

Section: Discussionmentioning

confidence: 99%

Effectiveness of Social Media in Road Traffic Congestion Management in Cities

2017

IJSR

View full text Add to dashboard Cite

Traffic congestion is common in major cities negatively impacting countries' economies. Conventional traffic control methods are unresponsive to emergent situations on the roads. Social media has become an integral part of peoples' lives in solving problems. This paper assesses its influence in traffic congestion management in cities. Four determinants are identified namely: users expected gain in status; obligation to others; unselfishness and direct compensation. The study found that social media usage positively influence road traffic management. Users derive satisfaction from active participation and selflessness. Social platforms unite users in a communication network where up-to-date traffic congestion information is propagated rapidly.

show abstract

Section: Discussionmentioning

confidence: 99%

Effectiveness of Social Media in Road Traffic Congestion Management in Cities

2017

IJSR

View full text Add to dashboard Cite

show abstract

“…Top words are then selected as keywords to acquire more traffic related tweets. Tokenization aims to break the short tweet text into separate tokens (Aziz et al, 2015;D'Andrea et al, 2015), and all the letters are normalized to lowercase (Aziz et al, 2015;Kurniawan et al, 2016;Yazici et al, 2017) at the same time. Non-English and duplicate posts (Kurniawan et al, 2016), accent marks (Ribeiro Jr. et al, 2012), and links and mentions to other Twitter accounts (Kurniawan et al, 2016;Ribeiro Jr. et al, 2012) are further removed.…”

Section: Wibirama Andmentioning

confidence: 99%

“…Non-English and duplicate posts (Kurniawan et al, 2016), accent marks (Ribeiro Jr. et al, 2012), and links and mentions to other Twitter accounts (Kurniawan et al, 2016;Ribeiro Jr. et al, 2012) are further removed. Filtering stop words, such as punctuations (Yazici et al, 2017) and non-alphanumeric (alphabets and numbers) characters (Kurniawan et al, 2016), are also an important step in the cleaning process (Aziz et al, 2015;D'Andrea et al, 2015;Kumar, Jiang, & Fang, 2014;Nguyen et al, 2016;Yazici et al, 2017). Moreover, as users may post a tweet with spelling errors and slangs, a replacement is required to make corrections .…”

Section: Wibirama Andmentioning

confidence: 99%

Sensing And Detecting Small-Scale Events Using Geosocial Media Data

Xu¹

2021

Preprint

View full text Add to dashboard Cite

<div>Small-scale events involve interactive human movement in limited space and time. Social media platforms possibly generate large amount of geospatially-referenced information related to small-scale events. It benefits individuals, management departments, and urban systems if small-scale events can be timely detected from social media platforms, where measuring the abnormal patterns of human movement to discover events and analyzing associated texts to interpret the reasons behind abnormal movement are two keys. Through investigating how people move as different events occur and measuring the patterns on social media platforms, small-scale events can be generally classified into two types, namely type I events with abrupt patterns and type II events with random occurrence of key factors, where social events and traffic events are representative correspondingly.</div><div>Despite many studies have been conducted to detect social events and traffic events using geosocial media data, there still are some un-answered questions requiring further research. Most existing studies did not identify occurring events from a full coverage of spatial, temporal, and semantic perspectives. Studies concerning social event detection lack efficient semantic analysis summarizing event content to infer the reasons driving the abnormal movement. The typical classification-based method regarding traffic event detection lacks investigation on how the spatiotemporal distribution of traffic relevant posts associate with the occurring traffic events, and simply assigns the detected events with predefined categories, missing events that indicate traffic anomalies but go beyond the predetermined categories.<br></div><div>In this thesis, spatial-temporal-semantic approaches are proposed to measure spatiotemporal patterns of posts and users of social media platforms to capture abnormal human movement, and analyze the content of associated posts to mine the reasons driving the movement. A variety of techniques including machine learning, natural language processing, and spatiotemporal analysis are adopted to realize effective detection. Based on one-year Twitter data collected in Toronto, 2014 Toronto International Film Festival and traffic anomaly detection are selected as two case studies to evaluate the performance of proposed approaches. Through comparing with the ground truth data, the result reveals that more than 80% of the detected events do refer to real-world events, which illustrates the feasibility and efficiency of proposed approaches.<br></div><div><br></div><div>Keywords: Small-scale event, Event detection, Geosocial media data, Traffic event, Social event, Twitter, Spatiotemporal clustering<br></div>

show abstract

“…Mochamad Vicky Ghani Aziz et al in [21] have used natural language processing to extract the traffic information from social media data. Twitter is used as the sample data.…”

Section: Comparative Analysismentioning

confidence: 99%

“…In [21], the result was not accurate due to poor preprocessing technique. Belainine Billal et al in [22] dedicated to a different methodology for preprocessing the big data such as twitter data so that the processed data can be useful for natural language processing.…”

Section: Comparative Analysismentioning

confidence: 99%

A Review on Information Retrieval – Natural Language Processing Approach

Vijayalakshmi¹,

Manasamithra²

2018

IJCA

View full text Add to dashboard Cite

Information retrieval is very important area in any of the IT applications. Systematic data storage is essential in information retrieval. In conventional method, data is stored in a structured format and retrieved using SQL queries which requires technical knowledge. Most common data storing and retrieving mechanism in IT is the Relational Database Management Systems. Now there is a necessity to retrieve data from a very large database using natural language from any social media. A brief survey of various methods used to store and retrieve data using Natural Language Processing (NLP) is carried out in this paper.

show abstract

Design and implementation of natural language processing with syntax and semantic analysis for extract traffic conditions from social media data

Cited by 12 publications

References 1 publication

Effectiveness of Social Media in Road Traffic Congestion Management in Cities

Effectiveness of Social Media in Road Traffic Congestion Management in Cities

Sensing And Detecting Small-Scale Events Using Geosocial Media Data

A Review on Information Retrieval – Natural Language Processing Approach

Contact Info

Product

Resources

About