Understanding climate change tweets: an open source toolkit for social media analysis

Maynard, Diana; Bontcheva, Kalina

doi:10.2991/ict4s-env-15.2015.28

Cited by 15 publications

(12 citation statements)

References 27 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By consisting of two environmental ontologies, GEMET (GEneral Multilingual Environmental Thesaurus) and Reegle, the ClimaPinion yields great results in recognizing environmental terms in text, with the precision, recall, and F1 measure of 85.87%, 53.05%, and 65.58% respectively (Maynard and Bontcheva, 2015).…”

Section: Discussionmentioning

confidence: 99%

Automatic Summarization of Online Debates

Sanchan¹,

Aker²,

Bontcheva³

2017

Proceedings of the Workshop Natural Language Processing and Information Retrieval

Self Cite

View full text Add to dashboard Cite

Debate summarization is one of the novel and challenging research areas in automatic text summarization which has been largely unexplored. In this paper, we develop a debate summarization pipeline to summarize key topics which are discussed or argued in the two opposing sides of online debates. We view that the generation of debate summaries can be achieved by clustering, cluster labeling, and visualization. In our work, we investigate two different clustering approaches for the generation of the summaries. In the first approach, we generate the summaries by applying purely term-based clustering and cluster labeling. The second approach makes use of X-means for clustering and Mutual Information for labeling the clusters. Both approaches are driven by ontologies. We visualize the results using bar charts. We think that our results are a smooth entry for users aiming to receive the first impression about what is discussed within a debate topic containing waste number of argumentations.

show abstract

Section: Discussionmentioning

confidence: 99%

Automatic Summarization of Online Debates

Sanchan¹,

Aker²,

Bontcheva³

2017

Proceedings of the Workshop Natural Language Processing and Information Retrieval

Self Cite

View full text Add to dashboard Cite

show abstract

“…The applications come from individuals with a scientific interest, professionals, startups and innovators that benefit from training in data science and social media analytics. 4 See Sect. 2.2.1 for detailed description of TA services.…”

Section: Fig 2 Sobigdata Management Boardsmentioning

confidence: 99%

Data science at SoBigData: the European research infrastructure for social mining and big data analytics

Grossi

Rapisarda

Giannotti

et al. 2018

Int J Data Sci Anal

View full text Add to dashboard Cite

Most people have become "big data" producers in their daily life. Our desires, opinions, sentiments, social links as well as our mobile phone calls and GPS track leave traces of our behaviours. To transform these data into knowledge, value is a complex task of data science. This paper shows how the SoBigData Research Infrastructure supports data science towards the new frontiers of big data exploitation. Our research infrastructure serves a large community of social sensing and social mining researchers and it reduces the gap between existing research centres present at European level. SoBigData integrates resources and creates an infrastructure where sharing data and methods among text miners, visual analytics researchers, socio-economic scientists, network scientists, political scientists, humanities researchers can indeed occur. The main concepts related to SoBigData Research Infrastructure are presented. These concepts support virtual and transnational (on-site) access to the resources. Creating and supporting research communities are considered to be of vital importance for the success of our research infrastructure, as well as contributing to train the new generation of data scientists. Furthermore, this paper introduces the concept of exploratory and shows their role in the promotion of the use of our research infrastructure. The exploratories presented in this paper represent also a set of real applications in the context of social mining. Finally, a special attention is given to the legal and ethical aspects. Everything in SoBigData is supervised by an ethical and legal framework.

show abstract

“…Some of these are found directly in ontologies such as GEMET, Reegle and DBpedia, while others are found (using linguistic techniques) as variants of such terms (e.g. alternative labels, or hyponyms of known terms) [17]. Using these annotations helps us to identify, from the timeline of each individual user, which of their posts are related to climate change and sustainability.…”

Section: Data Filteringmentioning

confidence: 99%

“…These included basic linguistic pre-processing (such as part-of-speech tagging and verb chunking) [9] and more complex tasks such as opinion mining and emotion detection [17]. The features initially extracted were:…”

Section: Feature Engineeringmentioning

confidence: 99%

“…Naturally, these users post about environmental issues, but they also post about their jobs, hobbies, personal experiences, and so on. To identify which of the content produced by the users relates to their environmental behaviour we used the Term Extraction tool ClimaTerm 11 developed in the context of this research and documented in [17]. ClimaTerm automatically identifies instances of environmental terms in text.…”

Section: Data Filteringmentioning

confidence: 99%

See 1 more Smart Citation

Talking climate change via social media

Fernández

Piccolo

Maynard

et al. 2016

Proceedings of the 8th ACM Conference on Web Science

Self Cite

View full text Add to dashboard Cite

While individual behaviour change is considered a central strategy to mitigate climate change, public engagement is still limited. Aiming to raise awareness, and to promote behaviour change, governments and organisations are conducting multiple pro-environmental campaigns, particularly via social media. However, to the best of our knowledge, these campaigns are neither based on, nor do they take advantage of, the existing theories and studies of behaviour change, to better target and inform users. In this paper we propose an approach for analysing user behaviour towards climate change based on the 5 Doors Theory of behaviour change [19]. Our approach automatically identifies five behavioural stages in which users are based on their social media contributions. This approach has been applied to analyse the online behaviour of participants of the Earth Hour 2015 and COP21 Twitter movements. Results of our analysis are used to provide guidelines on how to improve communication via these campaigns.

show abstract

Understanding climate change tweets: an open source toolkit for social media analysis

Cited by 15 publications

References 27 publications

Automatic Summarization of Online Debates

Automatic Summarization of Online Debates

Data science at SoBigData: the European research infrastructure for social mining and big data analytics

Talking climate change via social media

Contact Info

Product

Resources

About