Exploring the Potential of Twitter as a Research Tool

Ovadia, Steven

doi:10.1080/01639260903280888

Cited by 50 publications

(29 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Besides the traditional sharing of daily routines, users might share information of broad interest, for instance when multiple users report an event like an earthquake or a terrorist attack. There are a wide range of 978-1-4799-1959-8/15/$31.00 @2015 IEEE applications like event detection [1] - [4] , academic tool [5] [7] , news media [1] , [8] or mining political opinion [9] , [10] .…”

Section: Introductionmentioning

confidence: 99%

The impact of longstanding messages in micro-blogging classification

Costa

Silva

Antunes

et al. 2015

2015 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Social networks are making part of the daily routine of millions of users. Twitter is among Facebook and Instagram one of the most used, and can be seen as a relevant source of information as users share not only daily status, but rapidly propagate news and events that occur worldwide. Considering the dynamic nature of social networks, and their potential in information spread, it is imperative to find learning strategies able to learn in these environments and cope with their dynamic nature.Time plays an important role by easily out-dating information, being crucial to understand how informative can past events be to current learning models and for how long it is relevant to store previously seen information, to avoid the computation burden associated with the amount of data produced.In this paper we study the impact of longstanding messages in micro-blogging classification by using different training time window sizes in the learning process. Since there are few studies dealing with drift in Twitter and thus little is known about the types of drift that may occur, we simulate different types of drift in an artificial dataset to evaluate and validate our strategy. Results shed light on the relevance of previously seen examples according to different types of drift.

show abstract

Section: Introductionmentioning

confidence: 99%

The impact of longstanding messages in micro-blogging classification

Costa

Silva

Antunes

et al. 2015

2015 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

show abstract

“…The emergence of Symplur (Symplur, 2014) as a register and archive of healthcare hashtags provides a large databank of Twitter conversations around healthcare across all specialities including psychiatry. SoMe as a source of big data can be integrated with other offl ine data sources and monitored to gain an insight into current trends, and to identify opportunities in research (Ovadia, 2009) or potential collaborators. SoMe has changed the fl ow of information and led to a democratization of information (Quinton, 2013).…”

Section: Planningmentioning

confidence: 99%

“…While SoMe have been identifi ed as having the potential to change the way researchers work, collaborate and communicate (Archibald & Clark, 2014;Das et al, 2014;Grosseck & Holotescu, 2011;Kapp et al, 2013;Ovadia, 2009) both amongst themselves and with participants and the public, the actual use of SoMe in research is still in its infancy (O ' Connor, 2013;van Osch & Coursaris, 2014). In this paper we review some of the emerging evidence and commentaries on the adoption and role of SoMe in research which may inform their further application in medical and healthcare research.…”

Section: Introductionmentioning

confidence: 96%

Perspectives on social media in and as research: A synthetic review

Lafferty

Manca

2015

International Review of Psychiatry

View full text Add to dashboard Cite

With the growth of social media use in both the private and public spheres, researchers are currently exploring the new opportunities and practices offered by these tools in the research lifecycle. This area is still in its infancy: As methodological approaches and methods are being tested - mainly through pragmatic and exploratory approaches - practices are being shaped and negotiated by the actors involved in research. A further element of complexity is added by the ambivalent status of social media within research activities. They can be both a tool - for recruitment, data collection, analysis - and data - as what constitutes the corpus to be analysed - both in an observational and interactive domain. This synthetic analysis of the literature is aimed at identifying how social media are currently being used in research and how they fit into the research lifecycle. We identify and discuss emerging evidence and trends in the adoption of social media in research, which can be used and applied by psychiatry research practitioners as a framework to inform the development of a personalized research network and social media strategy in research.

show abstract

“…Although mostly considered as an entertainment tool, tweets may contain information of broad interest [5] and are being widely studied as they have a wide range of applications and uses, like event detection [6]- [9], academic tool [10]- [12], news media [6], [13] or mining political opinion [14], [15].…”

Section: Introductionmentioning

confidence: 99%

Concept Drift Awareness in Twitter Streams

Costa

Silva

Antunes

et al. 2014

2014 13th International Conference on Machine Learning and Applications

View full text Add to dashboard Cite

Learning in non-stationary environments is not an easy task and requires a distinctive approach. The learning model must not only have the ability to continuously learn, but also the ability to acquired new concepts and forget the old ones. Additionally, given the significant importance that social networks gained as information networks, there is an evergrowing interest in the extraction of complex information used for trend detection, promoting services or market sensing. This dynamic nature tends to limit the performance of traditional static learning models and dynamic learning strategies must be put forward.In this paper we present a learning strategy to learn with drift in the occurrence of concepts in Twitter. We propose three different models: a time-window model, an ensemble-based model and an incremental model. Since little is known about the types of drift that can occur in Twitter, we simulate different types of drift by artificially timestamping real Twitter messages in order to evaluate and validate our strategy. Results are so far encouraging regarding learning in the presence of drift, along with classifying messages in Twitter streams.

show abstract

Exploring the Potential of Twitter as a Research Tool

Cited by 50 publications

References 4 publications

The impact of longstanding messages in micro-blogging classification

The impact of longstanding messages in micro-blogging classification

Perspectives on social media in and as research: A synthetic review

Concept Drift Awareness in Twitter Streams

Contact Info

Product

Resources

About