Spatio‐temporal query contextualization for microtext retrieval in social media

Park, Jaehong; Lee, O-Joun; Jung, Jai E.

doi:10.1002/cpe.4458

Concurrency and Computation

2018

DOI: 10.1002/cpe.4458

|View full text |Cite

Spatio‐temporal query contextualization for microtext retrieval in social media

Jaehong Park

O-Joun Lee

Jai E. Jung

Abstract: Summary Generally, texts on the social media (eg, Twitter and Facebook) are too short (microtexts) to understand the meaning and to search for relevant texts. It is difficult for the conventional information retrieval systems to conduct the searching tasks. Thereby, in this paper, we propose a novel approach on query contextualization by integrating all possible microtexts by considering spatio‐temporal contexts. The proposed approach consists of two steps, which are (i) to understand and process microtexts in… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2018

2020

Publication Types

Select...

Article3

Relationship

Self Cite0

Independent3

Authors

Journals

Cited by 3 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Park et al propose a method for query expansion with contextual information called “Query Contextualization.” This method can remove the ambiguity of the queries by sensing and rebuilding the users' contextual information. As a result of experiments with actual SNS data, the authors confirmed that the concept changes based on spatio‐temporal information.…”

mentioning

confidence: 99%

Data fusion in the internet of data

Piccialli

Jung

2018

Concurrency and Computation

View full text Add to dashboard Cite

This special issue collates a selection of representative research articles that were primarily presented at the 2nd International Workshop on Data Mining on Internet of Things (IoT) Systems. This annual workshop brings together researchers and practitioners from both academia and industry who are working on data mining approaches on the IoT with applications in the Smart City framework and in the Cultural Heritage research domain in order to promote an exchange of ideas, discuss future collaborations, and develop new research directions.The Internet of Things envisages a plethora of heterogeneous objects interacting with the physical environments. It can be foreseen that IoT applications will raise the scale of data to an unprecedented level. Collecting, analyzing, and correlating data from different resources is a key role to drive smart interactions between actors of IoT environments.In this scenario, the Internet of Data (IoD) represents a concept of network composed by data entities coming from the Interne of Things (IoT).The IoD can be considered an extension of the IoT into the digital world, since the amount of data being collected is staggering. The opportunities created by IoD have the potential to be infinite. The IoD presents an ambitious purpose, ie, organizing the data to be interconnected as a network in order to infer useful information for data analysis and creates useful, customized, and location-based services.The scope of this special issue is broad and is representative of the multidisciplinary nature of the Internet of Data research field.Zheng et al 1 propose a term representation framework for four different features, ie, temporal feature, geographical feature, term co-occurrence, and hashtag. The framework deals with a series of attribution definition to detect topics on a Twitter dataset and confirm the effectiveness of LTDMF.The authors have also deeply analyze the importance of different features in topic detection.Kumar et al 2 present an efficient and secure time-limited hierarchical key assignment scheme key management suitable for data outsourcing scenario. They compare the proposed scheme with other recent similar schemes with respect to the cost of static and dynamic operations.The obtained results show that with similar unit private storage cost; the proposed scheme manages to reduce the key generation cost at the data owner and key derivation cost by each user.Wi and Tsai 3 propose a system to analyze at-home behavior and physiological indices of the elderly people. The design concepts for software and hardware equipment emphasize the following features: (1) low-cost sensor devices, (2) user-friendly interface for the wearable device, (3) easy installation for the equipment, and (4) low-power consumption for the wearable device.Experiment results show that the system simulation proves the algorithm to be feasible.Malik et al 4 discuss a data transformation methodology for geo-related semantic annotation and the importance of reducing the response time of investigation and offe...

show abstract

mentioning

confidence: 99%

Data fusion in the internet of data

Piccialli

Jung

2018

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

Short text similarity measurement using context‐aware weighted biterms

Yang

Huang

Ofoghi

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

With the development of internet technologies, social media and mobile devices, short texts have become an increasingly popular medium among users to communicate with friends, search information and review products. Measuring the similarity between short texts is a fundamental task due to its importance in many applications, such as text retrieval, topic discovery, and event detection. However, short texts generally comprise sparse, noisy, and ambiguous information. Hence, effectively measuring the distance between short texts is a challenging task. In this paper, we exploit the advantageous corpus-wide word co-occurrence information into document-level feature enrichment to mitigate the challenges caused by the sparseness of short texts for distance measurement. We propose a novel context-aware weighted Biterm method for short text Distance Measurement (BDM). In BDM, we extract biterms (ie, word pairs) from a short text corpus and exploit a biterm topic model to determine the global weights of biterms in the corpus. We then determine the local importance of a biterm in different contexts (ie, short texts) based on the corpus-level biterm weight. The distance between two short texts is computed using the context-aware weighted biterms. Experimental results on three real-world datasets demonstrate better accuracy and effectiveness of the proposed BDM.

show abstract

Cross-cultural contextualisation for recommender systems

Hong

Akerkar

et al. 2019

J Ambient Intell Human Comput

View full text Add to dashboard Cite

Cultural Heritage (CH) domain is rapidly moving from traditional heritage sites into smart cultural heritage environment through various technologies. As one of the important technologies in the smart space, Recommender Systems (RSs) have been widely utilised to personalised services and matching visitors' goals and behaviours. Whereas, cultural diíference is often considered a barrier to technology transfer or adoption. However, few studies focus on how the cultural factor influences recommendation despite cultural diíference largely aífects user preferences in the RSs. Furthermore, existing researches have mainly analysed evaluation results of their recommendation to reveal cultural diíferences, rather than utilising the cross-cultural factors into RSs. In this paper, we propose a novel concept of cross-cultural contextualisation and a model to compute the cross-cultural factor aífecting users (countries or cultures) preferences by using matrix factorisation and clustering techniques. In addition, we discuss how to apply the model to RSs in CH domain through cross-domain recommendation techniques. Note that the two computational techniques were used to analyse cross-cultural factors which impact to user preferences, rather than to recommend items. In other words, the proposed model and computing results capable of utilisation into the other RSs as well as various research fields. Results of experiments with a real-world dataset showed eífectiveness of the proposed model and supported that there is cultural diíference influencing users' rating behaviours. Furthermore, a systematic analysis of dataset and the experimental results presented that individual users could be considered as countrywise groups for the model to analyse the cross-cultural factors.

show abstract

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

customersupport@researchsolutions.com

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

Spatio‐temporal query contextualization for microtext retrieval in social media

Cited by 3 publications

References 15 publications

Data fusion in the internet of data

Data fusion in the internet of data

Short text similarity measurement using context‐aware weighted biterms

Cross-cultural contextualisation for recommender systems

Contact Info

Product

Resources

About