### Abstract

Society is often polarized by controversial issues that split the population into groups with opposing views. When such issues emerge on social media, we often observe the creation of 'echo chambers', i.e., situations where like-minded people reinforce each other's opinion, but do not get exposed to the views of the opposing side. In this paper we study algorithmic techniques for bridging these chambers, and thus reduce controversy. Specifically, we represent the discussion on a controversial issue with an endorsement graph, and cast our problem as an edge-recommendation problem on this graph. The goal of the recommendation is to reduce the controversy score of the graph, which is measured by a recently-developed metric based on random walks. At the same time, we take into account the acceptance probability of the recommended edge, which represents how likely the edge is to materialize in the endorsement graph. We propose a simple model based on a recently-developed user-level controversy score, that is competitive with state- of-the-art link-prediction algorithms. Our goal then becomes finding the edges that produce the largest reduction in the controversy score, in expectation. To solve this problem, we propose an efficient algorithm that considers only a fraction of all the possible combinations of edges. Experimental results show that our algorithm is more efficient than a simple greedy heuristic, while producing comparable score reduction. Fi- nally, a comparison with other state-of-the-art edge-addition algorithms shows that this problem is fundamentally different from what has been studied in the literature.

Original language | English |
---|---|

Title of host publication | WSDM 2017 - Proceedings of the 10th ACM International Conference on Web Search and Data Mining |

Publisher | Association for Computing Machinery, Inc |

Pages | 81-90 |

Number of pages | 10 |

ISBN (Electronic) | 9781450346757 |

DOIs | |

Publication status | Published - 2 Feb 2017 |

Event | 10th ACM International Conference on Web Search and Data Mining, WSDM 2017 - Cambridge, United Kingdom Duration: 6 Feb 2017 → 10 Feb 2017 |

### Other

Other | 10th ACM International Conference on Web Search and Data Mining, WSDM 2017 |
---|---|

Country | United Kingdom |

City | Cambridge |

Period | 6/2/17 → 10/2/17 |

### ASJC Scopus subject areas

- Computer Science Applications
- Information Systems
- Computer Networks and Communications
- Software

### Cite this

*WSDM 2017 - Proceedings of the 10th ACM International Conference on Web Search and Data Mining*(pp. 81-90). Association for Computing Machinery, Inc. https://doi.org/10.1145/3018661.3018703

**Reducing controversy by connecting opposing views.** / Garimella, Kiran; Morales, Gianmarco; Gionis, Aristides; Mathioudakis, Michael.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

*WSDM 2017 - Proceedings of the 10th ACM International Conference on Web Search and Data Mining.*Association for Computing Machinery, Inc, pp. 81-90, 10th ACM International Conference on Web Search and Data Mining, WSDM 2017, Cambridge, United Kingdom, 6/2/17. https://doi.org/10.1145/3018661.3018703

}

TY - GEN

T1 - Reducing controversy by connecting opposing views

AU - Garimella, Kiran

AU - Morales, Gianmarco

AU - Gionis, Aristides

AU - Mathioudakis, Michael

PY - 2017/2/2

Y1 - 2017/2/2

N2 - Society is often polarized by controversial issues that split the population into groups with opposing views. When such issues emerge on social media, we often observe the creation of 'echo chambers', i.e., situations where like-minded people reinforce each other's opinion, but do not get exposed to the views of the opposing side. In this paper we study algorithmic techniques for bridging these chambers, and thus reduce controversy. Specifically, we represent the discussion on a controversial issue with an endorsement graph, and cast our problem as an edge-recommendation problem on this graph. The goal of the recommendation is to reduce the controversy score of the graph, which is measured by a recently-developed metric based on random walks. At the same time, we take into account the acceptance probability of the recommended edge, which represents how likely the edge is to materialize in the endorsement graph. We propose a simple model based on a recently-developed user-level controversy score, that is competitive with state- of-the-art link-prediction algorithms. Our goal then becomes finding the edges that produce the largest reduction in the controversy score, in expectation. To solve this problem, we propose an efficient algorithm that considers only a fraction of all the possible combinations of edges. Experimental results show that our algorithm is more efficient than a simple greedy heuristic, while producing comparable score reduction. Fi- nally, a comparison with other state-of-the-art edge-addition algorithms shows that this problem is fundamentally different from what has been studied in the literature.

AB - Society is often polarized by controversial issues that split the population into groups with opposing views. When such issues emerge on social media, we often observe the creation of 'echo chambers', i.e., situations where like-minded people reinforce each other's opinion, but do not get exposed to the views of the opposing side. In this paper we study algorithmic techniques for bridging these chambers, and thus reduce controversy. Specifically, we represent the discussion on a controversial issue with an endorsement graph, and cast our problem as an edge-recommendation problem on this graph. The goal of the recommendation is to reduce the controversy score of the graph, which is measured by a recently-developed metric based on random walks. At the same time, we take into account the acceptance probability of the recommended edge, which represents how likely the edge is to materialize in the endorsement graph. We propose a simple model based on a recently-developed user-level controversy score, that is competitive with state- of-the-art link-prediction algorithms. Our goal then becomes finding the edges that produce the largest reduction in the controversy score, in expectation. To solve this problem, we propose an efficient algorithm that considers only a fraction of all the possible combinations of edges. Experimental results show that our algorithm is more efficient than a simple greedy heuristic, while producing comparable score reduction. Fi- nally, a comparison with other state-of-the-art edge-addition algorithms shows that this problem is fundamentally different from what has been studied in the literature.

UR - http://www.scopus.com/inward/record.url?scp=85015262963&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85015262963&partnerID=8YFLogxK

U2 - 10.1145/3018661.3018703

DO - 10.1145/3018661.3018703

M3 - Conference contribution

AN - SCOPUS:85015262963

SP - 81

EP - 90

BT - WSDM 2017 - Proceedings of the 10th ACM International Conference on Web Search and Data Mining

PB - Association for Computing Machinery, Inc

ER -