Ranking content based on semantic dimensions

A multi-objective approach

Jason Cohn, Siddharth Muthukumaran, Lawrence A Birnbaum

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Whether it’s a social media system populating a news feed or a user searching for content to share, decisions are constantly being made on the basis of semantic information. Topic, sentiment, and preference are among the many semantic dimensions of content that humans and machines must carefully weigh when prioritizing media consumption. Though easy for humans, such natural language tasks are nontrivial computationally. In this paper, we present a novel technique for sorting a corpus of news articles based on two competing semantic objectives. Solving this multi-objective optimization problem yields a pareto front with a finite set of solution articles. Iterating on the remaining data, we construct solution sets in tiers of successive pareto fronts. Our technique allows for exploration of the tradeoffs between semantic concepts, yielding cogent and trope-like results.

Original languageEnglish (US)
Title of host publicationProceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2017
PublisherAssociation for Computing Machinery, Inc
Pages605-608
Number of pages4
ISBN (Electronic)9781450349932
DOIs
StatePublished - Jul 31 2017
Event9th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2017 - Sydney, Australia
Duration: Jul 31 2017Aug 3 2017

Other

Other9th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2017
CountryAustralia
CitySydney
Period7/31/178/3/17

Fingerprint

Semantics
Multiobjective optimization
Sorting

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Information Systems

Cite this

Cohn, J., Muthukumaran, S., & Birnbaum, L. A. (2017). Ranking content based on semantic dimensions: A multi-objective approach. In Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2017 (pp. 605-608). Association for Computing Machinery, Inc. https://doi.org/10.1145/3110025.3120992
Cohn, Jason ; Muthukumaran, Siddharth ; Birnbaum, Lawrence A. / Ranking content based on semantic dimensions : A multi-objective approach. Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2017. Association for Computing Machinery, Inc, 2017. pp. 605-608
@inproceedings{ea79ac23dbc64895a478e7de6ec4d726,
title = "Ranking content based on semantic dimensions: A multi-objective approach",
abstract = "Whether it’s a social media system populating a news feed or a user searching for content to share, decisions are constantly being made on the basis of semantic information. Topic, sentiment, and preference are among the many semantic dimensions of content that humans and machines must carefully weigh when prioritizing media consumption. Though easy for humans, such natural language tasks are nontrivial computationally. In this paper, we present a novel technique for sorting a corpus of news articles based on two competing semantic objectives. Solving this multi-objective optimization problem yields a pareto front with a finite set of solution articles. Iterating on the remaining data, we construct solution sets in tiers of successive pareto fronts. Our technique allows for exploration of the tradeoffs between semantic concepts, yielding cogent and trope-like results.",
author = "Jason Cohn and Siddharth Muthukumaran and Birnbaum, {Lawrence A}",
year = "2017",
month = "7",
day = "31",
doi = "10.1145/3110025.3120992",
language = "English (US)",
pages = "605--608",
booktitle = "Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2017",
publisher = "Association for Computing Machinery, Inc",

}

Cohn, J, Muthukumaran, S & Birnbaum, LA 2017, Ranking content based on semantic dimensions: A multi-objective approach. in Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2017. Association for Computing Machinery, Inc, pp. 605-608, 9th IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2017, Sydney, Australia, 7/31/17. https://doi.org/10.1145/3110025.3120992

Ranking content based on semantic dimensions : A multi-objective approach. / Cohn, Jason; Muthukumaran, Siddharth; Birnbaum, Lawrence A.

Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2017. Association for Computing Machinery, Inc, 2017. p. 605-608.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Ranking content based on semantic dimensions

T2 - A multi-objective approach

AU - Cohn, Jason

AU - Muthukumaran, Siddharth

AU - Birnbaum, Lawrence A

PY - 2017/7/31

Y1 - 2017/7/31

N2 - Whether it’s a social media system populating a news feed or a user searching for content to share, decisions are constantly being made on the basis of semantic information. Topic, sentiment, and preference are among the many semantic dimensions of content that humans and machines must carefully weigh when prioritizing media consumption. Though easy for humans, such natural language tasks are nontrivial computationally. In this paper, we present a novel technique for sorting a corpus of news articles based on two competing semantic objectives. Solving this multi-objective optimization problem yields a pareto front with a finite set of solution articles. Iterating on the remaining data, we construct solution sets in tiers of successive pareto fronts. Our technique allows for exploration of the tradeoffs between semantic concepts, yielding cogent and trope-like results.

AB - Whether it’s a social media system populating a news feed or a user searching for content to share, decisions are constantly being made on the basis of semantic information. Topic, sentiment, and preference are among the many semantic dimensions of content that humans and machines must carefully weigh when prioritizing media consumption. Though easy for humans, such natural language tasks are nontrivial computationally. In this paper, we present a novel technique for sorting a corpus of news articles based on two competing semantic objectives. Solving this multi-objective optimization problem yields a pareto front with a finite set of solution articles. Iterating on the remaining data, we construct solution sets in tiers of successive pareto fronts. Our technique allows for exploration of the tradeoffs between semantic concepts, yielding cogent and trope-like results.

UR - http://www.scopus.com/inward/record.url?scp=85040233412&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85040233412&partnerID=8YFLogxK

U2 - 10.1145/3110025.3120992

DO - 10.1145/3110025.3120992

M3 - Conference contribution

SP - 605

EP - 608

BT - Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2017

PB - Association for Computing Machinery, Inc

ER -

Cohn J, Muthukumaran S, Birnbaum LA. Ranking content based on semantic dimensions: A multi-objective approach. In Proceedings of the 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, ASONAM 2017. Association for Computing Machinery, Inc. 2017. p. 605-608 https://doi.org/10.1145/3110025.3120992