974 Hits in 3.9 sec

Bots and Gender Profiling using a Multi-layer Architecture

Régis Goubin, Dorian Lefeuvre, Alaa Alhamzeh, Jelena Mitrovic, Elöd Egyed-Zsigmond, Leopold Ghemmogne Fossi
2019 Conference and Labs of the Evaluation Forum  
We then used a 2-layers architecture to predict the gender of the users detected as humans.  ...  author profiling participation. In this task, we had to predict if the author of 100 tweets was a bot, a female human, or a male human user.  ...  On the final submission we use the following features for bot classification: - Gender Prediction The gender prediction is based on a 2-layer architecture.  ... 
dblp:conf/clef/GoubinLAMEF19 fatcat:5nijqixdtzelphh6637o5gqjfe

Twitter Demographic Classification Using Deep Multi-modal Multi-task Learning

Prashanth Vijayaraghavan, Soroush Vosoughi, Deb Roy
2017 Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)  
Our classifier uses a deep multi-modal multitask learning architecture to reach a stateof-the-art performance, achieving an F1score of 0.89, 0.82, 0.86, and 0.68 for gender, age, political orientation,  ...  In this paper, we present a demographic classifier for gender, age, political orientation and location on Twitter. We collected and curated a robust Twitter demographic dataset for this task.  ...  We also collected and curated a novel Twitter demographic dataset and explored different variants of deep multi-modal multi-task learning architectures, settling on the Hierarchical-Attention DMT as the  ... 
doi:10.18653/v1/p17-2076 dblp:conf/acl/VijayaraghavanV17 fatcat:5ifzroxslrbrzfejy55ifrqjeq

Online User Profiling to Detect Social Bots on Twitter [article]

Maryam Heidari, James H Jr Jones, Ozlem Uzuner
2022 arXiv   pre-print
The new proposed model for bot detection creates user profiles based on personal information such as age, personality, gender, education from users' online posts and introduces a machine learning model  ...  Online users' profile shows the user's personal information, such as age, gender, education, and personality. In this work, the user's profile is constructed based on the user's online posts.  ...  The bidirectional multi-layer LSTM uses the history of backward and forward tokens for each target token in a tweet's text.  ... 
arXiv:2203.05966v1 fatcat:wyzrsyaenfbjznjzhvl5xvgroa

Bot and Gender Identification from Twitter

Radarapu Rakesh, Yogesh Vishwakarma, Akkajosyula Surya Sai Gopal, Anand Kumar M
2019 Conference and Labs of the Evaluation Forum  
This working note is capitalized on earlier approaches and Machine Learning (ML) approaches used to classify between a bot and human and find the gender further for interesting studies in crime detection  ...  By sharing many attributes for user profiles, we have identified the pattern to find out that the given user is a bot or human based on the tweets posted.  ...  Introduction Before we dive into the proposed methodology used for solving the Bot and Gender identification task, let us have a look at why Author Profiling is needed and its effects on society.  ... 
dblp:conf/clef/RakeshVGM19 fatcat:rjlh76mnx5dj5enfwzye7ddugu

BeCAPTCHA: Behavioral Bot Detection using Touchscreen and Mobile Sensors benchmarked on HuMIdb [article]

Alejandro Acien and Aythami Morales and Julian Fierrez and Ruben Vera-Rodriguez and Oscar Delgado-Mohatar
2020 arXiv   pre-print
The goal of BeCAPTCHA is to determine whether the drag and drop task was realized by a human or a bot.  ...  The heterogeneous flow of data generated during the interaction with the smartphones can be used to model human behavior when interacting with the technology and improve bot detection algorithms.  ...  The Generator learns the human features of the swipe gestures and generate human-like ones from Gaussian Noise and human sequences T , A . the dense layer is used as a classification layer to distinguish  ... 
arXiv:2005.13655v2 fatcat:z7ch5rxn2zevzpimsalmo4vrv4

Author Profiling on Social Media: An Ensemble Learning Approach using Various Features

Youngjun Joo, Inchon Hwang
2019 Conference and Labs of the Evaluation Forum  
We describe our participation in the PAN 2019 shared task on author profiling, determine whether a tweet's author is a bot or a human, and in case of human, identify author's gender for English and Spanish  ...  Our proposed model obtained 0.9333 and 0.8352 of accuracy in the bot and gender identification tasks for English test dataset respectively.  ...  In the 2019 shared AP task on PAN dataset [2] , the goal is to infer whether the author of a Twitter feed is a bot or a human and to profile the author's gender in case of human [16] .  ... 
dblp:conf/clef/JooH19 fatcat:7ceztesujncmrpml5b55cxl2jq

Deep Learning Empowered Cybersecurity Spam Bot Detection for Online Social Networks

Mesfer Al Duhayyim, Haya Mesfer Alshahrani, Fahd N. Al-Wesabi, Mohammed Alamgeer, Anwer Mustafa Hilal, Mohammed Rizwanullah
2022 Computers Materials & Continua  
With this motivation, the current research article proposes a Spam Bot Detection technique using Hybrid DL model abbreviated as SBD-HDL.  ...  Both hybridization of GCN-RNN and LOA-based hyperparameter tuning process make the current work, a first-of-its-kind in this domain.  ...  Accuracy can be determined as a ratio of properly classified user profiles over total number of available user profiles and can be defined using Eq. ( 11 ): Accuracy = TP + TN TP + FN + FP + TN (11)  ... 
doi:10.32604/cmc.2022.021212 fatcat:4ckxs6ghs5b43jkxldx5u4mwb4

Using Hashtags and POS-Tags for Author Profiling

Flurin Gishamer
2019 Conference and Labs of the Evaluation Forum  
It will be shown that the segmentation of hashtags as well as using POS-Tags n-grams can increase the accuracy when classifying bot and gender on the PAN Twitter-dataset.  ...  This paper investigates automatic methods to separate human created from bot created Tweets, and in the case of human, determine the gender of an author.  ...  Martin Braschler for his valuable and constructive contribution to the planning and development of this paper. His feedback as a supervisor has always been of great value to me.  ... 
dblp:conf/clef/Gishamer19 fatcat:3hbqzo2d3renhhxefocspmdqoi

Identification of Fake vs. Real Identities on Social Media using Random Forest and Deep Convolutional Neural Network

2019 International Journal of Engineering and Advanced Technology  
The fake identities are categorized into two main types' i.e. fake identities by bots and fake identities by humans.  ...  Here, dataset used is that of Twitter.  ...  ANN could be a assortment of nodes organized in layers. it's three main layers: input layer, hidden layer and output layer.  ... 
doi:10.35940/ijeat.a9739.109119 fatcat:lduxxk3m7jfzbo7dxaavs2trfa

A Social Media Tax Data Warehouse to Manage the Underground Economy

Aaron Groulx, Carolyn McGregor
2018 2018 IEEE 20th International Conference on High Performance Computing and Communications; IEEE 16th International Conference on Smart City; IEEE 4th International Conference on Data Science and Systems (HPCC/SmartCity/DSS)  
The warehouse also incorporates the use of social media analytics to support tax evasion detection and enforcement activities such as compliance risk assessment, audits, inspections and investigations.  ...  This paper proposes a data warehouse design to integrate social media data into tax analytics processes.  ...  The proposed design is a multi-layer data warehouse architecture that facilitates the extraction, processing and storage of integrated social media and tax data, along with end user data analysis capabilities  ... 
doi:10.1109/hpcc/smartcity/dss.2018.00261 dblp:conf/hpcc/GroulxM18 fatcat:2n3jsq3usve2dapzyn32mngkiu

A Deep Learning Approach for Robust Detection of Bots in Twitter using Transformers

David Martin-Gutierrez, Gustavo Hernandez Penaloza, Alberto Belmonte-Hernandez, Alicia Lozano-Diez, Federico Alvarez
2021 IEEE Access  
Moreover, the Bot-DenseNet produces a low-dimensional representation of the user account which can be used for any application within the Information Retrieval (IR) framework.  ...  the rest of the metadata to build a potential input vector on top of a Dense Network denoted as Bot-DenseNet.  ...  ACKNOWLEDGMENT This work was supported by the H2020 European Project: FAke News discovery and propagation from big Data ANalysis and artificial intelliGence Operations (FANDANGO). Grant no. 780355.  ... 
doi:10.1109/access.2021.3068659 fatcat:mb646hcs7rdwbawxpuhvakffmq

MSDF: A General Open-Domain Multi-Skill Dialog Framework [article]

Yu Zhao, Xinshuo Hu, Yunxin Li, Baotian Hu, Dongfang Li, Sichao Chen, Xiaolong Wang
2022 arXiv   pre-print
Dialog systems have achieved significant progress and have been widely used in various scenarios.  ...  In this paper, we propose a general Multi-Skill Dialog Framework, namely MSDF, which can be applied in different dialog tasks (e.g. knowledge grounded dialog and persona based dialog).  ...  ) and Stable Support Program for Higher Education Institutions of Shenzhen (No.  ... 
arXiv:2206.08626v1 fatcat:mnv5t3yul5dulmx2ghoiu4ojsm

Tweet-Based Bot Detection Using Big Data Analytics

Abdelouahid Derhab, Rahaf Alawwad, Khawlah Dehwah, Noshina Tariq, Farrukh Aslam Khan, Jalal Al-Muhtadi
2021 IEEE Access  
A simple CNN architecture was used to classify textual tweets into bot or human. The model consisted of two-dimensional convolutional layers, two max-pooling layers, and two dropout layers of 50%.  ...  ) N/A 93% N/A N/A 80% [31] ASW EC2 6M N/A N/A N/A Twitter statistics + Category vector + Sentiment + LDA Graph neu- ral network N/A 89% N/A N/A N/A [32] Bots and Gender Profiling  ... 
doi:10.1109/access.2021.3074953 fatcat:n4womre6cbdddbe5oeqrivn4hy

Virtual agent modeling in the RASCALLI platform

Christian Eis, Marcin Skowron, Brigitte Krenn
2008 Proceedings of the 8th Workshop on Performance Metrics for Intelligent Systems - PerMIS '08  
Due to the underlying software architecture and the modularity of the agents, it allows the parallel execution and evaluation of multiple agents.  ...  The RASCALLI platform is both a runtime and a development environment for virtual systems augmented with cognition.  ...  This layer consists of the following sub-layers: Agent Architecture Layer: An agent architecture is a blueprint defining the architectural core of a particular type of Rascalli.  ... 
doi:10.1145/1774674.1774686 dblp:conf/permis/EisSK08 fatcat:mgfpumnaxjgurct3euqobuenwq

TwiBot-20: A Comprehensive Twitter Bot Detection Benchmark [article]

Shangbin Feng, Herun Wan, Ningnan Wang, Jundong Li, Minnan Luo
2021 arXiv   pre-print
We reproduce competitive bot detection methods and conduct a thorough evaluation on TwiBot-20 and two other public datasets.  ...  To alleviate these problems, we present TwiBot-20, a massive Twitter bot detection benchmark, which contains 229,573 users, 33,488,192 tweets, 8,723,736 user property items and 455,958 follow relationships  ...  PAN-19 4 is a dataset of a Bots and Gender Profiling shared task in the PAN workshop at CLEF 2019. It is used for bots and gender profiling and contains user semantic information.  ... 
arXiv:2106.13088v2 fatcat:k5eydukpgrbffdwgkwrdu3f5kq
« Previous Showing results 1 — 15 out of 974 results