People

@article{hosseinmardi2019discovering,

title = {Discovering hidden structure in high dimensional human behavioral data via tensor factorization},

author = {Homa Hosseinmardi and Hsien-Te Kao and Kristina Lerman and Emilio Ferrara},

url = {https://arxiv.org/pdf/1905.08846.pdf},

doi = {10.475/123_4},

year  = {2019},

date = {2019-05-21},

pages = {5},

abstract = {In recent years, the rapid growth in technology has increased the opportunity for longitudinal human behavioral studies. Rich multimodal data, from wearables like Fitbit, online social networks, mobile phones etc. can be collected in natural environments. Uncovering the underlying low-dimensional structure of noisy multi-way data in an unsupervised setting is a challenging problem. Tensor factorization has been successful in extracting the interconnected low-dimensional descriptions of multi-way data. In this paper, we apply non-negative tensor factorization on a real-word wearable sensor data, StudentLife, to find latent temporal factors and group of similar individuals. Meta data is available for the semester schedule, as well as the individuals’ performance and personality. We demonstrate that non-negative tensor factorization can successfully discover clusters of individuals who exhibit higher academic performance, as well as those who frequently engage in leisure activities. The recovered latent temporal patterns associated with these groups are validated against ground truth data to demonstrate the accuracy of our framework.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{kao2019understanding,

title = {Understanding Cyberbullying on Instagram and Ask.fm via Social Role Detection},

author = {Hsien-Te Kao and Shen Yan and Di Huang and Nathan Bartley and Homa Hosseinmardi and Emilio Ferrara},

url = {https://dl.acm.org/doi/abs/10.1145/3308560.3316505},

doi = {10.1145/3308560.3316505},

year  = {2019},

date = {2019-05-13},

journal = {Companion Proceedings of The 2019 World Wide Web Conference},

pages = {183-188},

abstract = {Cyberbullying is a major issue on online social platforms, and can have prolonged negative psychological impact on both the bullies and their targets. Users can be characterized by their involvement in cyberbullying according to different social roles including victim, bully, and victim supporter. In this work, we propose a social role detection framework to understand cyberbullying on online social platforms, and select a dataset that contains users’ records on both Instagram and Ask.fm as a case study. We refine the traditional victim-bully framework by constructing a victim-bully-supporter network on Instagram. These social roles are automatically identified via ego comment networks and linguistic cues of comments. Additionally, we analyze the consistency of users’ social role within Instagram and compare users’ behaviors on Ask.fm. Our analysis reveals the inconsistency of social roles both within and across platforms, which suggests social roles in cyberbullying are not invariant by conversation, person, or social platform.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{ghasemian2019evaluating,

title = {Evaluating overfit and underfit in models of network community structure},

author = {Amir Ghasemian and Homa Hosseinmardi and Aaron Clauset},

url = {https://arxiv.org/pdf/1802.10582},

year  = {2019},

date = {2019-04-16},

journal = {IEEE Transactions on Knowledge and Data Engineering},

volume = {32},

number = {9},

pages = {1722-1735},

abstract = {A common graph mining task is community detection, which seeks an unsupervised decomposition of a network into groups based on statistical regularities in network connectivity. Although many such algorithms exist, community detection’s No Free Lunch theorem implies that no algorithm can be optimal across all inputs. However, little is known in practice about how different algorithms over or underfit to real networks, or how to reliably assess such behavior across algorithms. Here, we present a broad investigation of over and underfitting across 16 state-of-the-art community detection algorithms applied to a novel benchmark corpus of 572 structurally diverse real-world networks. We find that (i) algorithms vary widely in the number and composition of communities they find, given the same input; (ii) algorithms can be clustered into distinct high-level groups based on similarities of their outputs on real-world networks; (iii) algorithmic differences induce wide variation in accuracy on link-based learning tasks; and, (iv) no algorithm is always the best at such tasks across all inputs. Finally, we quantify each algorithm’s overall tendency to over or underfit to network data using a theoretically principled diagnostic, and discuss the implications for future advances in community detection.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}