Wearing Many (Social) Hats: How Different Are Your Different Social Network Personae?

Zhong, Changtao; Chang, Hau Wen; Karamshuk, Dmytro; Lee, Dongwon; Sastry, Nishanth

doi:10.1609/icwsm.v11i1.14897

Cited by 16 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…demonstrate the implications for cross-platform prediction. customize user bios to suit particular social media platforms (Zhong et al 2017) in order to be socially desirable (Edwards 1957), as well as the need to associate -for instance, self-identify as the member of a certain age group or community (Papacharissi 2002). We hypothesize that the influence of self-categorization and social desirability would be observed in the individual choices to post certain messages on Facebook versus Twitter, and the relationship of user traits with honest vs. positive self-presentation.…”

Section: Introductionmentioning

confidence: 99%

Facebook versus Twitter: Differences in Self-Disclosure and Trait Prediction

Jaidka

Guntuku

Ungar

2018

ICWSM

View full text Add to dashboard Cite

This study compares self-disclosure on Facebook and Twitter through the lens of demographic and psychological traits. Predictive evaluation reveals that language models trained on Facebook posts are more accurate at predicting age, gender, stress, and empathy than those trained on Twitter posts. Qualitative analyses of the underlying linguistic and demographic differences reveal that users are significantly more likely to disclose information about their family, personal concerns, and emotions and provide a more `honest' self-representation on Facebook. On the other hand, the same users significantly preferred to disclose their needs, drives, and ambitions on Twitter. The higher predictive performance of Facebook is also partly due to the greater volume of language on Facebook than Twitter -- Facebook and Twitter are equally good at predicting user traits when the same-sized language samples are used to train language models. We explore the implications of these differences in cross-platform user trait prediction.

show abstract

Section: Introductionmentioning

confidence: 99%

Facebook versus Twitter: Differences in Self-Disclosure and Trait Prediction

Jaidka

Guntuku

Ungar

2018

ICWSM

View full text Add to dashboard Cite

show abstract

“…Our findings also reiterate previous research on language use in mental health (De Choudhury et al 2013). An important insight from our work was that the predictive utility of different platforms varies, as has been seen in prior research looking at differences in self-disclosure (Jaidka et al 2018;Zhong et al 2017). This motivates the need for transfer learning when the stress model trained on Facebook language needs to be applied to Twitter language.…”

Section: Discussionmentioning

confidence: 69%

“…Then, we evaluate how models trained on Facebook perform at predicting stress from Twitter language in a crossdomain setting. Previous studies showed that predictive performance changes in cross-domain applications (Jaidka et al 2018;Zhong et al 2017). Therefore, we then attempt to Facebook Twitter User Engagement (Lin et al 2014) .11 .05 TensiStrength (Thelwall 2017) .17…”

Section: Methodsmentioning

confidence: 99%

Understanding and Measuring Psychological Stress Using Social Media

Guntuku

Buffone

Jaidka

et al. 2019

ICWSM

View full text Add to dashboard Cite

A body of literature has demonstrated that users’ mental health conditions, such as depression and anxiety, can be predicted from their social media language. There is still a gap in the scientific understanding of how psychological stress is expressed on social media. Stress is one of the primary underlying causes and correlates of chronic physical illnesses and mental health conditions. In this paper, we explore the language of psychological stress with a dataset of 601 social media users, who answered the Perceived Stress Scale questionnaire and also consented to share their Facebook and Twitter data. Firstly, we find that stressed users post about exhaustion, losing control, increased self-focus and physical pain as compared to posts about breakfast, family-time, and travel by users who are not stressed. Secondly, we find that Facebook language is more predictive of stress than Twitter language. Thirdly, we demonstrate how the language based models thus developed can be adapted and be scaled to measure county-level trends. Since county-level language is easily available on Twitter using the Streaming API, we explore multiple domain adaptation algorithms to adapt user-level Facebook models to Twitter language. We find that domain-adapted and scaled social mediabased measurements of stress outperform sociodemographic variables (age, gender, race, education, and income), against ground-truth survey-based stress measurements, both at the user- and the county-level in the U.S. Twitter language that scores higher in stress is also predictive of poorer health, less access to facilities and lower socioeconomic status in counties. We conclude with a discussion of the implications of using social media as a new tool for monitoring stress levels of both individuals and counties.

show abstract

“…Self-disclosure is also influenced by the type of content found on differing social media platforms. These observations are relevant to note in netnography as it may provide an explanation as to why self-disclosure in the online communities, and the "personalities" that come with it, can vary across different social media platforms [32]. As different platforms, and their respective content, are used by individuals of varying demographics, it is often observed that individuals' self-disclosure behaviors will be based on the level of risk and reward that a specific platform may bring them [32].…”

Section: Self-disclosurementioning

confidence: 94%

A Place for Women and Women's Issues: An Examination of Narratives on Postpartum Depression Self-Disclosure on Pinterest

Fenton,

Erak,

Konkle

2023

Preprint

View full text Add to dashboard Cite

This study aimed to expand and inform the growing body of research on Postpartum Depression, from a netnographic standpoint, for the social media platform of Pinterest. More specifically, it aimed to assess the type of content present on Pinterest regarding Postpartum Depression shared by women in 2018 and 2021, as well as examine the subjective experience of women who have experienced this mood disorder. Data were collected following a search using the keywords “Postpartum Depression” on Pinterest on two separate timestamps (2018 and 2021); pins were limited to those in English or French. Master themes were identified among all pins and those identified as “self-disclosure” were subsequently further analyzed. Self-disclosure data were separately analysed using thematic analysis, specifically adopting a deductive thematic approach for the 2021 data set stemming from the coding scheme created from analysis of the 2018 data. Major themes were identified, and an analysis of frequency was performed for each sub-theme, along with qualitative examples associated with each theme. A total of 483 Pinterest pins from two different time points of 2018 (169 pins) and 2021 (314 sample pins) were analyzed. Five primary categories were identified in both 2018 and 2021, with five additional categories being identified in the 2021 dataset. Comparative results from 2018 and 2021 self-disclosure pins show individuals’ varying yet similar subjective manifestations of PPD, the potential need to adopt a multidisciplinary treatment approach, and the societal fears, such as mental health stigma, that are playing a part in help-seeking behavior hesitancies. Our findings provide imperative insight into individuals’ subjective experiences with PPD; experiences that involve a sensitive and vulnerable topic. Netnographic research, along with Pinterest, must be taken into consideration for future work delving into women’s health issues, including those surrounding perinatal mental health.

show abstract

Wearing Many (Social) Hats: How Different Are Your Different Social Network Personae?

Cited by 16 publications

References 24 publications

Facebook versus Twitter: Differences in Self-Disclosure and Trait Prediction

Facebook versus Twitter: Differences in Self-Disclosure and Trait Prediction

Understanding and Measuring Psychological Stress Using Social Media

A Place for Women and Women's Issues: An Examination of Narratives on Postpartum Depression Self-Disclosure on Pinterest

Contact Info

Product

Resources

About