Twitter n-gram corpus with demographic metadata

Herdağdelen, Amaç

doi:10.1007/s10579-013-9227-2

Cited by 24 publications

(19 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The same process is applied for female users. The accuracy of this process was 97.85%, with approximately symmetric error rates for either gender: 2.94% of the females and 2.35% of the males (Herdağdelen, 2013).…”

Section: Research Papermentioning

confidence: 86%

See 1 more Smart Citation

Twitter Users’ Privacy Concerns: What do Their Accounts’ First Names Tell Us?

Espinosa

Xiao

2018

Journal of Data and Information Science

View full text Add to dashboard Cite

Purpose In this paper, we describe how gender recognition on Twitter can be used as an intelligent business tool to determine the privacy concerns among users, and ultimately offer a more personalized service for customers who are more likely to respond positively to targeted advertisements. Design/methodology/approach We worked with two different data sets to examine whether Twitter users’ gender, inferred from the first name of the account and the profile description, correlates with the privacy setting of the account. We also used a set of features including the inferred gender of Twitter users to develop classifiers that predict user privacy settings. Findings We found that the inferred gender of Twitter users correlates with the account’s privacy setting. Specifically, females tend to be more privacy concerned than males. Users whose gender cannot be inferred from their provided first names tend to be more privacy concerned. In addition, our classification performance suggests that inferred gender can be used as an indicator of the user’s privacy preference. Research limitations It is known that not all twitter accounts are real user accounts, and social bots tweet as well. A major limitation of our study is the lack of consideration of social bots in the data. In our study, this implies that at least some percentage of the undefined accounts, that is, accounts that had names non-existent in the name dictionary, are social bots. It will be interesting to explore the privacy setting of social bots in the Twitter space. Practical implications Companies are investing large amounts of money in business intelligence tools that allow them to know the preferences of their consumers. Due to the large number of consumers around the world, it is very difficult for companies to have direct communication with each customer to anticipate market changes. For this reason, the social network Twitter has gained relevance as one ideal tool for information extraction. On the other hand, users’ privacy preference needs to be considered when companies consider leveraging their publicly available data. This paper suggests that gender recognition of Twitter users, based on Twitter users’ provided first names and their profile descriptions, can be used to infer the users’ privacy preference. Originality/value This study explored a new way of inferring Twitter user’s gender, that is, to recognize the user’s gender based on the provided first name and the user’s profile description. The potential of this information for predicting the user’s privacy preference is explored.

show abstract

Section: Research Papermentioning

confidence: 86%

“…In order to increase the size of our database we included the names that appeared in the American population census of 1960-2010 (Herdağdelen, 2013) and the most popular names in America in 1990 (Herdağdelen, 2013). Our database has 19,562 unique names (9019 female names, 10,563 male names).…”

Section: Name Databasementioning

confidence: 99%

Twitter Users’ Privacy Concerns: What do Their Accounts’ First Names Tell Us?

Espinosa

Xiao

2018

Journal of Data and Information Science

View full text Add to dashboard Cite

show abstract

“…Also, with aim to filter uncommon or low quality variants, the Rovereto Twitter corpus (Herdagdelen, 2013) was initially used in order to rank the English candidates present in the corpus by their frequencies. The 38% of the variants generated by one transformation were successfully found, however, performing direct Twitter search API queries resulted to have better coverage than using a static corpus (90% for English variants).…”

Section: Candidate Selectionmentioning

confidence: 99%

Mining Lexical Variants from Microblogs: An Unsupervised Multilingual Approach

Mosquera¹,

Pozo²

2014

Proceedings of the 5th Workshop on Language Analysis for Social Media (LASM)

View full text Add to dashboard Cite

User-generated content has become a recurrent resource for NLP tools and applications, hence many efforts have been made lately in order to handle the noise present in short social media texts. The use of normalisation techniques has been proven useful for identifying and replacing lexical variants on some of the most informal genres such as microblogs. But annotated data is needed in order to train and evaluate these systems, which usually involves a costly process. Until now, most of these approaches have been focused on English and they were not taking into account demographic variables such as the user location and gender. In this paper we describe the methodology used for automatically mining a corpus of variant and normalisation pairs from English and Spanish tweets.

show abstract

“…A research done by (Herdağdelen, 2013) was concentrated on a potential combining of an n-gram text corpus from twitter messages with demographics metadata. He used these messages coupled with metadata about their authors to understand a wide variety of phenomena ranging from political polarization to geographic and demographic lexical variation.…”

Section: Related Workmentioning

confidence: 99%

Gender Prediction of Journalists from Writing Style

Ali

Surameery

Yunis³

et al. 2013

ARO

View full text Add to dashboard Cite

Abstract-Web-based Kurdish media have seen a tangible growth in the last few years. There are many factors that have contributed into this rapid growth. These include an easy access to the internet connection, the low price of electronic gadgets and pervasive usage of social networking. The swift development of the Kurdish web-based media imposes new challenges that need to be addressed. For example, a newspaper article published online possesses properties such as author name, gender, age, and nationality among others. Determining one or more of these properties, when ambiguity arises, using computers is an important open research area. In this study the journalist's gender in web-based Kurdish media determined using computational linguistic and text mining techniques. 75 webbased Kurdish articles used to train artificial model designed to determine the gender of journalists in web-based Kurdish media. Articles were downloaded from four different well known webbased Kurdish newspapers. 61 features were extracted from each article; these features are distinct in discriminating between genders. The Multi-Layer Perceptron (MLP) artificial neural network is used as a classification technique and the accuracy received were 76%.

show abstract

Twitter n-gram corpus with demographic metadata

Cited by 24 publications

References 21 publications

Twitter Users’ Privacy Concerns: What do Their Accounts’ First Names Tell Us?

Twitter Users’ Privacy Concerns: What do Their Accounts’ First Names Tell Us?

Mining Lexical Variants from Microblogs: An Unsupervised Multilingual Approach

Gender Prediction of Journalists from Writing Style

Contact Info

Product

Resources

About