Anonymous Hyperlocal Communities in Saudi Arabia
Unveiling the dynamics of anonymous hyperlocal communities in Saudi Arabia through a comprehensive study featuring unique design features, communication intents, and the impact of anonymity and hyperlocality. Delve into the intricacies of user interactions, posting motivations, and cultural environments within these distinct online spaces.
Download Presentation
Please find below an Image/Link to download the presentation.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.
You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.
The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.
E N D
Presentation Transcript
Content in Content in Anonymous Anonymous Hyperlocal Communities Hyperlocal Communities Saudi Arabia in the spotlight Jens Helge Reelfs , Oliver Hohlfeld , Niklas Henckell Brandenburg University of Technology The Jodel Venture GmbH International Workshop on Location and the Web April 26, 2022 1
Motivation Motivation Content in Social Media Content in Social Media Motivation Motivation Content in Social Media Content in Social Media Community Feed 24/7 everyday communication Lots of platforms RW focuses single (US/EU) markets We focus on Jodel in SA Unique design features Anonymity Hyperlocality Given these very same features What do Users talk about? What is the intent for posting? But WHY SA? a Jodel (thread) Distinct Communities (by design) Communciation Intents & Topics Up-/Downvote & Karma Content in Anonymous Hyperlocal Communities 2
Related Work Related Work Focus US/EU markets Hyperlocality <> Location Based SN Surveys Information & entertainment [1,2] social, local, and anonymous identity [3] (Self) Supervised Learning ephemeral in an impersonal [4] no personal information [4] Spatial topic distances [5] Personal Admission, General Entertainment & Info [3] Anonymity Toxicy yes/no [1,6] Broader Topics/More personal [7] Topics [8] Dating & Sex, Local Life & Weather, Education & Work, Health & Drugs, Politics & Religion Intents [3,9] Personal Admission, Observation, Information & Advice, Opinion, Venting/Complaining Cultural Environment Internet provides open spaces to KSA women [10] Driving Ban Lift, Integration of Woman Labor Questionable freedom of speech within KSA [11] Content in Anonymous Hyperlocal Communities 3
Hyperlocality (I) Hyperlocality (I) Posts / Replies bound to location N Content in Anonymous Hyperlocal Communities 4
Hyperlocality (I) Hyperlocality (I) Posts / Replies bound to location N Content in Anonymous Hyperlocal Communities 5
*https://en.wikipedia.org/wiki/Saudi_Arabia Used Dataset & Corpus Used Dataset & Corpus Ground truth information from operator Textual content - 15k random sample Hashtag occurrences Type SA Users 1.2M Content 469M Interactions 961M Content in Anonymous Hyperlocal Communities 6
Interaction Volume steep Usage Increase So, WHAT happened here? Time Content in Anonymous Hyperlocal Communities 7
Approach to Approach to Intents Intents & & Topics Topics Classifcation Schema Crowdsourcing Campagins Evaluation Content in Anonymous Hyperlocal Communities 8
Classification Schema & Campagin Design Classification Schema & Campagin Design Schema Goal Intents Topics Trade-Off Coverage (few Other) Non-Overlap Minimal Set Begin with prior work [5,10,16] Iterative refinement on random samples Study Design Focus on Thread start 2 Expert Annotators Learn Schema Discuss & Create Coherence Multiple runs Content in Anonymous Hyperlocal Communities 9
Classification Schema & Campagin Design Classification Schema & Campagin Design Schema Goal Intents Topics Trade-Off Coverage (few Other) Non-Overlap Minimal Set Begin with prior work [5,10,16] Iterative refinement on random samples Study Design Focus on Thread start 2 Expert Annotators Learn Schema Discuss & Create Coherence Multiple runs Content in Anonymous Hyperlocal Communities 10
Results Results In line with Related Work Intents Topics People & Relationships Seeking Interaction/Information Self (Personal) Self Expression Other Coverage could be better Entertainment & Culture Other Beliefs & Politics Social Media Social Venting & Complaints Fashion & Beauty Information Sharing Education & Work Products & Services General Entertainment Food & Drink Fitness & Health Distress Releae & Complaints Animals & Nature Entertaining Observation Illegal & Violence 0 500 1000 1500 2000 2500 0 500 1000 1500 2000 2500 Content in Anonymous Hyperlocal Communities 11 especially includes localation-related content
Campagign & Schema Quality (I) Campagign & Schema Quality (I) Agreement (Krippendorf Alpha + weighting) Mostly substantial Only moderate on Topics at times Qualitative Annotator Feedback Non-Toxic Young People / Teenagers Seeking interaction (games, other sex) Content in Anonymous Hyperlocal Communities 12
Campagign & Schema Quality (II) Campagign & Schema Quality (II) Multi-Annotator Confusion Intent Confusion relatively low Topic Confusion higher Precision could be better No Model is perfect. Content in Anonymous Hyperlocal Communities 13
Inhomogeneity Inhomogeneity: Jeddah vs. Riyadh more content Jeddah In Riyadh broader spectrum more content Riyadh Focus on Entertainment In Jeddah Differences in Social Media Usage Exist Between Western and Middle-East Countries 14
Qualitative Insights: Qualitative Insights: Top Hashtags Top Hashtags The Story of Happy Marriages 1. Kissing 2. Things that turn you on 3. Marriages Hopes & Fears 4. Why Single? 5. Matchmaking 6. Marriage Conditions 7. First Night in Marriage 8. Behavior During Sexual Intercourse Hashtag _ Hashtag _ # _ _ # #your_sexual_orientation _ #Honest_matchmaking #name_of_a_girl_you_wish_to_date _ _ _ _ #say_your_name_and_we_guess_if_you_are_hot_or_not _ _ # # _ _ _ _ _ # # #Share_karma_count_and_get_upvotes _ #wild_questions _ #forbidden_desire _ #matchmake_each_other # #confessions _ #things_which_turn_you_on_in_wome n _ #why_single _ _ #messages_which_will_never_arrive #a_move_that_turns_you_on _ #your_age_and_get_hooked_up _ #raise_the_karma_campaign _ #confession_chair _ #say_i_love_you_to_a_random_name _ _ #a_campaign_for_friendship_your_name_your_gender # # _ # # # # _ _ # _ _ # # #jodel_speech _ _ _ _ # # _ _ # # #the_first_person_to_comment_can_ask_a_favor Content in Anonymous Hyperlocal Communities 15
Summary Summary Created Annotation Schema Intents Topics Crowdsourced Annotation Campaigns Agreement moderate/substantial Schema has weaknesses (trade-off) Findings in line with RW No toxicity Predominant: Entertainment, Seeking Interaction, Social Venting, Self Expression Inhomogeneous Spatial Communities Classifcation Schema Crowdsourcing Campagins Evaluation Content in Anonymous Hyperlocal Communities 16
Check out the paper Check out the paper for more! for more! ... now it is time for discussions. https://h.reelfs.de Content in Anonymous Hyperlocal Communities 17
Empirical Measures Empirical Measures Content in Anonymous Hyperlocal Communities 18
