Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Opinion-aware Influence Maximization in Online Social Networks

Ying Wang, Yanhao Wang

TL;DR

The paper addresses selecting seed users to maximize positive information spread while curbing negative sentiment in online networks. It introduces Opinion-aware Influence Maximization (OIM) under an opinion-aware IC model, leveraging historical data and GNN-based representations to classify user opinions and estimate diffusion. The method combines reverse reachable (RR) sets for opinion-aware influence estimation with a sandwich greedy seed-selection strategy based on the difference of submodular bounds, yielding data-dependent approximation guarantees. Experiments on three real-world datasets show that OIM improves positive opinion spread and reduces negative spread with competitive runtime, offering a practical approach for opinion-conscious viral promotion.

Abstract

Influence maximization (IM) aims to find seed users on an online social network to maximize the spread of information about a target product through word-of-mouth propagation among all users. Prior IM methods mostly focus on maximizing the overall influence spread, which assumes that all users are potential customers of the product and that more exposure leads to higher benefits. However, in real-world scenarios, some users who dislike the product may express and spread negative opinions, damaging the product's reputation and lowering its profit. This paper investigates the opinion-aware influence maximization (OIM) problem, which finds a set of seed users to maximize the positive opinions toward the product while minimizing the negative opinions. We propose a novel algorithm for the OIM problem. Specifically, after obtaining the users with positive and negative opinions towards the product from historical data, we design a reverse reachable set-based method for opinion-aware influence estimation and a sandwich approximation algorithm for seed set selection. Despite the NP-hardness and non-submodularity of OIM, our algorithm achieves a data-dependent approximation factor for OIM. Experimental results on three real-world datasets demonstrate that our algorithm improves the spread of positive opinions while reducing the spread of negative opinions compared to existing methods.

Opinion-aware Influence Maximization in Online Social Networks

TL;DR

The paper addresses selecting seed users to maximize positive information spread while curbing negative sentiment in online networks. It introduces Opinion-aware Influence Maximization (OIM) under an opinion-aware IC model, leveraging historical data and GNN-based representations to classify user opinions and estimate diffusion. The method combines reverse reachable (RR) sets for opinion-aware influence estimation with a sandwich greedy seed-selection strategy based on the difference of submodular bounds, yielding data-dependent approximation guarantees. Experiments on three real-world datasets show that OIM improves positive opinion spread and reduces negative spread with competitive runtime, offering a practical approach for opinion-conscious viral promotion.

Abstract

Influence maximization (IM) aims to find seed users on an online social network to maximize the spread of information about a target product through word-of-mouth propagation among all users. Prior IM methods mostly focus on maximizing the overall influence spread, which assumes that all users are potential customers of the product and that more exposure leads to higher benefits. However, in real-world scenarios, some users who dislike the product may express and spread negative opinions, damaging the product's reputation and lowering its profit. This paper investigates the opinion-aware influence maximization (OIM) problem, which finds a set of seed users to maximize the positive opinions toward the product while minimizing the negative opinions. We propose a novel algorithm for the OIM problem. Specifically, after obtaining the users with positive and negative opinions towards the product from historical data, we design a reverse reachable set-based method for opinion-aware influence estimation and a sandwich approximation algorithm for seed set selection. Despite the NP-hardness and non-submodularity of OIM, our algorithm achieves a data-dependent approximation factor for OIM. Experimental results on three real-world datasets demonstrate that our algorithm improves the spread of positive opinions while reducing the spread of negative opinions compared to existing methods.
Paper Structure (10 sections, 5 theorems, 8 equations, 4 figures, 1 table, 1 algorithm)

This paper contains 10 sections, 5 theorems, 8 equations, 4 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. Problem Formulation
  4. Our Algorithm
  5. Opinion-aware Influence Estimation
  6. Seed Selection
  7. Experiments
  8. Setup
  9. Experimental Results
  10. Conclusion

Key Result

Lemma 1

For a seed set $S \subseteq V$, a node $u \in V$, and an RR set $\mathcal{R}_u$ of node $u$, we have $\Pr[S \leadsto u] = \Pr[\mathcal{R}_u \cap S \neq \emptyset]$.

Figures (4)

  • Figure 1: Illustration for opinion-aware IM in an OSN.
  • Figure 2: Counterexamples for the monotonicity and submodularity of OIM.
  • Figure 3: Total opinions and running time of OIM by varying the error parameter $\varepsilon$.
  • Figure 4: Total opinions and running time of different algorithms by varying the seed set size $k$.

Theorems & Definitions (11)

  • Definition 1
  • Example 1
  • Lemma 1
  • Lemma 2
  • proof
  • Lemma 3
  • proof
  • Lemma 4
  • proof
  • Theorem 1
  • ...and 1 more