Similarity vs. Diversity

By Barry Smyth, Paul McClave. 2001

480 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Networks and Communications

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Networks and Communications

Citations in the corpus

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, neutral): “Likewise, certain AI problems (such as content recommendation or information retrieval) also aim at producing diverse recommendations rather than highly-scoring yet similar results [405,406] .”
Retrieval, reuse, revision and retention in case-based reasoning (2005, unknown): “They demonstrate how their model of competence (Smyth & McKenna, 1998; 2001a) can be used to prioritise gaps in case knowledge and, like McSherry (2000; 2001a), propose a technique for automatically suggesting the type of cases that an author might want to consider to fill these gaps with a view to…”
Recommender Systems (2012, background): “Approaches to this problem include direct enhancement of the recommendation list’s diversity [36–38] and the use of hybrid recommendation methods [39].”
Computing Recommendations via a Knowledge Graph-aware Autoencoder (2018, background): “Nonetheless, it has been argued [40] that also diversity should be taken into account when evaluating users’ satisfaction.”
Introduction to Recommender Systems Handbook (2011, background): “• Diversity of the items recommended to a target user [104, 66, 69, 55, 54, 46, 119].”
Do not blame it on the algorithm: an empirical assessment of multiple recommender systems and their impact on content diversity (2018, unknown): “In fact, algorithmic design can also increase diversity (Smyth & McClave, 2001).”
Multistakeholder recommendation: Survey and research directions (2020, background): “See, for example, Abdollahpouri et al. (2017a), Smyth and McClave (2001), Ziegler et al. (2005), Vargas and Castells (2011), Jannach and Adomavicius (2016) and Abdollahpouri et al. (2019a).”
Evaluating Recommendation Systems (2011, background): “In recommenders that assist in information search (see Chapter 18), we can assume that more diverse recommendations will result in shorter search interactions [55].”
Evaluating recommender systems from the user’s perspective: survey of the state of the art (2012, background): “Thus, in recent years, more researchers have focused on generating diverse recommendations and aiming to reach an optimal balance between diversity and similarity (McGinty and Smyth 2003; Ziegler et al. 2005; Smyth and McClave 2001; Pu and Chen 2006).”
Recommender systems based on user reviews: the state of the art (2015, methodology): “Diversity is computed as the average pairwise product dissimilarity in the recommendation list (Smyth and McClave 2001).”
Case-based recommender systems (2005, background): “The ﬁrst in-depth investigation of the role of diversity in recommender systems appeared in Smyth & McClave (2001).”
Temporal diversity in recommender systems (2010, methodology): “For example, Smyth and McClave [11] apply strategies to improve recommender systems based on cased-based reasoning; diversity, in this case, is viewed as the complement of similarity.”
Diversity, Serendipity, Novelty, and Coverage (2016, methodology): “We adopted the definition of diversity that is based on the average pairwise item distance, which is widely accepted in the RS literature [Smyth and McClave 2001; Ziegler et al. 2005; Kelly and Bridge 2006; Vargas and Castells 2011] As mentioned in Section 2.1, the item distance function dist(i, j)…”