Comparing Recommendations Made by Online Systems and Friends

By R. Sinha, Kirsten Swearingen. DELOS Workshops / Conferences, 2001

553 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/a2399a7a0b39ade27f9edf605075f3fa3877e2c9

How researchers see this paper

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

Citations in the corpus

Evaluating Recommender Systems with User Experiments (2015, background): “For example, one of the first user-centric evaluations of a recommender system, conducted by Sinha and Swearingen [104], employs only 19 participants.”
Recommender Systems: Introduction and Challenges (2015, background): “Evidence suggests that people tend to rely more on recommendations from their friends than on recommendations from similar but anonymous individuals [52].”
Evaluating recommender systems from the user’s perspective: survey of the state of the art (2012, background): “…that providing good explanations for recommendations could help inspire users’ trust and satisfaction, increase users’ involvement and educate users on the internal logic of the system (Herlocker et al. 2000; Sinha and Swearingen 2001, 2002; Simonson 2005; Tintarev and Masthoff 2007a,b).”
Explaining Recommendations (2007, unknown): “In a literature survey (see [7] for details) we have identified seven different criteria by which explanations for single recommendations have been evaluated with users in the past: transparency [12], scrutability [13], trust [10, 14], effectiveness [1], persuasiveness [5], efficiency [15], and sati”
Recommender Systems (2012, background): “Social filtering Recommendations made by a recommender system are often less appreciated than those coming from our friends [210] and social influences may play a more important role than similarity of past activities [211, 212].”
A user-centric evaluation framework for recommender systems (2011, background): “In addition, it is useful to use relative accuracy to compare the difference between recommendations a user may get from a system versus those from friends [28].”
Organizational Behavior and Human Decision Processes (2019, unknown): “On the one hand, in subjective domains governed by personal taste, people relied on friends over algorithmic recommender systems for book, movie, and joke recommendations (Sinha & Swearingen, 2001; Yeomans, Shah, Mullainathan, & Kleinberg, unpublished data).”
Resistance to Medical Artificial Intelligence (2019, unknown): “…nonmedical settings, including in predicting employee performance (Kuncel et al. 2013), market demand (Sanders and Manrodt 2003), fraud (Boatsman et al. 1997), crime (Kleinberg et al. 2018; Wormith and Goldstone 1984), and consumer preferences (Sinha and Swearingen 2001; Yeomans et al. 2019).”
Recommender systems: from algorithms to user experience (2012, background): “And Sinha and Swearingen (2001) found that users find recommendations from friends to be more useful than those from “systems,” even though the recommender systems have a greater range of items over which to provide accurate predictions.”
Investigating interactions of trust and interest similarity (2007, background): “In fact, automated collaborative filtering systems exploit this conjecture in order to make reliable predictions of product preference [57].”
E-Commerce Product Recommendation Agents: Use, Characteristics, and Impact (2007, background): “Sinha and Swearingen, in a series of studies involving RAs in different domains (Sinha and Swearingen 2001, 2002; Swearingen and Sinha 2001, 166 MIS Quarterly Vol. 31 No. 1/March 2007 2002), also confirmed that explanations can enhance perceptions of the transparency of RAs’ inner workings, which…”
A Survey of Collaborative Filtering Techniques (2009, background): “The weight of a class’s AUC is the class’s frequency in the data [129, 132].”
Use of social network information to enhance collaborative filtering performance (2010, background): “Sinha and Swearingen (2001) compared the quality of recommendations made by recommender systems and by users' friends.”
Data Mining for Web Personalization (2007, background): “User studies have shown that users ﬁnd online recommenders most useful when they recommend unexpected items [124], suggesting that using content similarity alone may result in missing important “pragmatic” relationships among Web objects such as their common or complementary utility in the context…”
Inspectability and control in social recommenders (2012, background): “Sinha and Swearingen [42] demonstrate that users rate systems that provide detailed information about recommended items as more useful and easier to use.”