What kind of #conversation is Twitter? Mining #psycholinguistic cues for emergency coordination

Purohit, Hemant; Hampton, Andrew; Shalin, Valerie L.; Sheth, Amit P.; Flach, John M.; Bhatt, Shreyansh

doi:10.1016/j.chb.2013.05.007

Cited by 62 publications

(44 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tweets contain a wealth of data, and mining this data can provide insight into public opinion and behaviour responses in particular situations (Chew and Eysenbach, 2010). Twitter was described by Purohit et al (2013) as a microblogging platform that acts as a medium for the flow of information where users can post from other users.…”

Section: Twittermentioning

confidence: 99%

“…For example, although, as we indicated in the previous section, people may not be fully aware that their Tweets are publicly viewable, some researchers (Townsend & Wallace, 2016) argue that if a tweet contains a hashtag, then the user tweeting this has intended for their tweet to be visible to a broader audience, and therefore informed consent is not necessary when reproducing the tweet in an academic article. Purohit et al (2013) described the key features of Twitter:…”

Section: Twittermentioning

confidence: 99%

“…The mention feature T  A new feature implemented after the paper by Purohit et al (2013) was published is that…”

Section: Twittermentioning

confidence: 99%

See 2 more Smart Citations

Chapter 4: Using Twitter as a Data Source: An Overview of Ethical, Legal, and Methodological Challenges

Ahmed¹,

Bath²,

Demartini³

2017

Advances in Research Ethics and Integrity

126

View full text Add to dashboard Cite

Purpose: This chapter provides an overview of the specific legal, ethical, and privacy issues that can arise when conducting research using Twitter data. Approach:We review existing literature to inform those whom may be undertaking social media research. We also present a number of industry and academic case studies in order to highlight the challenges that may arise in research projects using social media data. Finally, the chapter provides an overview of the process that was followed to gain ethics approval for a PhD project using Twitter as a primary source of data.Practical Implications: By outlining a number of Twitter-specific research case studies the chapter is a valuable resource to those considering the ethical implications of their own research projects utilizing social media data. Moreover, the chapter outlines existing work looking at the ethical practicalities of social media data, and relates their applicability to researching Twitter.Value: This chapter is a potentially useful resource to those conducting social media research, or those who wish to gain an understanding of the specific legal, ethical, and privacy issues that can face social media researchers.

show abstract

Section: Twittermentioning

confidence: 99%

Section: Twittermentioning

confidence: 99%

See 1 more Smart Citation

Chapter 4: Using Twitter as a Data Source: An Overview of Ethical, Legal, and Methodological Challenges

Ahmed¹,

Bath²,

Demartini³

2017

Advances in Research Ethics and Integrity

126

View full text Add to dashboard Cite

show abstract

“…[23], which asserted that "the" assumes a previously established topic. Often discarded as stopwords, we rather consider such conversational indicator categories to be social behavior patterns (see Table II), as studied for conversation classification in [24]. To factor in the degree of conversationality, instead of creating a binary feature for the pattern, we create term frequency based numerical features for each of the conversational indicator categories.…”

Section: ) V1: Bottom-up Processingmentioning

confidence: 99%

Intent Classification of Short-Text on Social Media

Purohit

Dong

Shalin

et al. 2015

2015 IEEE International Conference on Smart City/SocialCom/SustainCom (SmartCity)

Self Cite

View full text Add to dashboard Cite

Abstract-Social media platforms facilitate the emergence of citizen communities that discuss real-world events. Their content reflects a variety of intent ranging from social good (e.g., volunteering to help) to commercial interest (e.g., criticizing product features). Hence, mining intent from social data can aid in filtering social media to support organizations, such as an emergency management unit for resource planning. However, effective intent mining is inherently challenging due to ambiguity in interpretation, and sparsity of relevant behaviors in social data. In this paper, we address the problem of multiclass classification of intent with a use-case of social data generated during crisis events. Our novel method exploits a hybrid feature representation created by combining top-down processing using knowledge-guided patterns with bottom-up processing using a bag-of-tokens model. We employ pattern-set creation from a variety of knowledge sources including psycholinguistics to tackle the ambiguity challenge, social behavior about conversations to enrich context, and contrast patterns to tackle the sparsity challenge. Our results show a significant absolute gain up to 7% in the F1 score relative to a baseline using bottom-up processing alone, within the popular multiclass frameworks of One-vs-One and One-vs-All. Intent mining can help design efficient cooperative information systems between citizens and organizations for serving organizational information needs.

show abstract

“…This is built into an argument that citizens have a critical role to play in supporting the public services under such circumstances. (See also Mandel et al, [2012] and Purohit et al [2013] for other treatments of the same kind of material). Also popular are examinations of the use of Twitter during major news events.…”

mentioning

confidence: 99%

Microblog Analysis as a Program of Work

Tolmie

Procter

Rouncefield

et al. 2018

Trans. Soc. Comput.

View full text Add to dashboard Cite

Inspired by a European project, PHEME, that requires the close analysis of Twitter-based conversations in order to look at the spread of rumors via social media, this paper has two objectives. The first of these is to take the analysis of microblogs back to first principles and lay out what microblog analysis should look like as a foundational programme of work. The other is to describe how this is of fundamental relevance to Human-Computer Interaction's interest in grasping the constitution of people's interactions with technology within the social order. Our critical finding is that, despite some surface similarities, Twitterbased conversations are a wholly distinct social phenomenon requiring an independent analysis that treats them as unique phenomena in their own right, rather than as another species of conversation that can be handled within the framework of existing Conversation Analysis. This motivates the argument that Microblog Analysis be established as a foundationally independent programme, examining the organizational characteristics of microblogging from the ground up. We articulate how aspects of this approach have already begun to shape our design activities within the PHEME project.• Human-centred computing➝Human computer interaction (HCI) • Collaborative and social computing➝Social media.

show abstract

What kind of #conversation is Twitter? Mining #psycholinguistic cues for emergency coordination

Cited by 62 publications

References 12 publications

Chapter 4: Using Twitter as a Data Source: An Overview of Ethical, Legal, and Methodological Challenges

Chapter 4: Using Twitter as a Data Source: An Overview of Ethical, Legal, and Methodological Challenges

Intent Classification of Short-Text on Social Media

Microblog Analysis as a Program of Work

Contact Info

Product

Resources

About