People commonly need to purchase things in person, from large garden supplies to home decor. Although modern search systems are very effective at finding online products, little research attention has been paid to helping users find places that sell a specific product offline. For instance, users searching for an apron are not typically directed to a nearby kitchen store by a standard search engine. In this paper, we investigate "where can I buy"-style queries related to in-person purchases of products and services. Answering these queries is challenging since little is known about the range of products sold in many stores, especially those which are smaller in size. To better understand this class of queries, we first present an in-depth analysis of typical offline purchase needs as observed by a major search engine, producing an ontology of such needs. We then propose ranking features for this new problem, and learn a ranking function that returns stores most likely to sell a queried item or service, even if there is very little information available online about some of the stores. Our final contribution is a new evaluation framework that combines distance with store relevance in measuring the effectiveness of such a search system. We evaluate our method using this approach and show that it outperforms a modern web search engine.
{"title":"Where Can I Buy a Boulder?: Searching for Offline Retail Locations","authors":"Sandro Bauer, Filip Radlinski, Ryen W. White","doi":"10.1145/2872427.2882998","DOIUrl":"https://doi.org/10.1145/2872427.2882998","url":null,"abstract":"People commonly need to purchase things in person, from large garden supplies to home decor. Although modern search systems are very effective at finding online products, little research attention has been paid to helping users find places that sell a specific product offline. For instance, users searching for an apron are not typically directed to a nearby kitchen store by a standard search engine. In this paper, we investigate \"where can I buy\"-style queries related to in-person purchases of products and services. Answering these queries is challenging since little is known about the range of products sold in many stores, especially those which are smaller in size. To better understand this class of queries, we first present an in-depth analysis of typical offline purchase needs as observed by a major search engine, producing an ontology of such needs. We then propose ranking features for this new problem, and learn a ranking function that returns stores most likely to sell a queried item or service, even if there is very little information available online about some of the stores. Our final contribution is a new evaluation framework that combines distance with store relevance in measuring the effectiveness of such a search system. We evaluate our method using this approach and show that it outperforms a modern web search engine.","PeriodicalId":20455,"journal":{"name":"Proceedings of the 25th International Conference on World Wide Web","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86217225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Gilad Tsur, Yuval Pinter, Idan Szpektor, David Carmel
Vertical selection is the task of predicting relevant verticals for a Web query so as to enrich the Web search results with complementary vertical results. We investigate a novel variant of this task, where the goal is to detect queries with a question intent. Specifically, we address queries for which the user would like an answer with a human touch. We call these CQA-intent queries, since answers to them are typically found in community question answering (CQA) sites. A typical approach in vertical selection is using a vertical's specific language model of relevant queries and computing the query-likelihood for each vertical as a selective criterion. This works quite well for many domains like Shopping, Local and Travel. Yet, we claim that queries with CQA intent are harder to distinguish by modeling content alone, since they cover many different topics. We propose to also take the structure of queries into consideration, reasoning that queries with question intent have quite a different structure than other queries. We present a supervised classification scheme, random forest over word-clusters for variable length texts, which can model the query structure. Our experiments show that it substantially improves classification performance in the CQA-intent selection task compared to content-oriented based classification, especially as query length grows.
{"title":"Identifying Web Queries with Question Intent","authors":"Gilad Tsur, Yuval Pinter, Idan Szpektor, David Carmel","doi":"10.1145/2872427.2883058","DOIUrl":"https://doi.org/10.1145/2872427.2883058","url":null,"abstract":"Vertical selection is the task of predicting relevant verticals for a Web query so as to enrich the Web search results with complementary vertical results. We investigate a novel variant of this task, where the goal is to detect queries with a question intent. Specifically, we address queries for which the user would like an answer with a human touch. We call these CQA-intent queries, since answers to them are typically found in community question answering (CQA) sites. A typical approach in vertical selection is using a vertical's specific language model of relevant queries and computing the query-likelihood for each vertical as a selective criterion. This works quite well for many domains like Shopping, Local and Travel. Yet, we claim that queries with CQA intent are harder to distinguish by modeling content alone, since they cover many different topics. We propose to also take the structure of queries into consideration, reasoning that queries with question intent have quite a different structure than other queries. We present a supervised classification scheme, random forest over word-clusters for variable length texts, which can model the query structure. Our experiments show that it substantially improves classification performance in the CQA-intent selection task compared to content-oriented based classification, especially as query length grows.","PeriodicalId":20455,"journal":{"name":"Proceedings of the 25th International Conference on World Wide Web","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80646159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yang Li, Shulong Tan, Huan Sun, Jiawei Han, D. Roth, Xifeng Yan
Named Entity Disambiguation is the task of disambiguating named entity mentions in natural language text and link them to their corresponding entries in a reference knowledge base (e.g. Wikipedia). Such disambiguation can help add semantics to plain text and distinguish homonymous entities. Previous research has tackled this problem by making use of two types of context-aware features derived from the reference knowledge base, namely, the context similarity and the semantic relatedness. Both features heavily rely on the cross-document hyperlinks within the knowledge base: the semantic relatedness feature is directly measured via those hyperlinks, while the context similarity feature implicitly makes use of those hyperlinks to expand entity candidates' descriptions and then compares them against the query context. Unfortunately, cross-document hyperlinks are rarely available in many closed domain knowledge bases and it is very expensive to manually add such links. Therefore few algorithms can work well on linkless knowledge bases. In this work, we propose the challenging Named Entity Disambiguation with Linkless Knowledge Bases (LNED) problem and tackle it by leveraging the useful disambiguation evidences scattered across the reference knowledge base. We propose a generative model to automatically mine such evidences out of noisy information. The mined evidences can mimic the role of the missing links and help boost the LNED performance. Experimental results show that our proposed method substantially improves the disambiguation accuracy over the baseline approaches.
{"title":"Entity Disambiguation with Linkless Knowledge Bases","authors":"Yang Li, Shulong Tan, Huan Sun, Jiawei Han, D. Roth, Xifeng Yan","doi":"10.1145/2872427.2883068","DOIUrl":"https://doi.org/10.1145/2872427.2883068","url":null,"abstract":"Named Entity Disambiguation is the task of disambiguating named entity mentions in natural language text and link them to their corresponding entries in a reference knowledge base (e.g. Wikipedia). Such disambiguation can help add semantics to plain text and distinguish homonymous entities. Previous research has tackled this problem by making use of two types of context-aware features derived from the reference knowledge base, namely, the context similarity and the semantic relatedness. Both features heavily rely on the cross-document hyperlinks within the knowledge base: the semantic relatedness feature is directly measured via those hyperlinks, while the context similarity feature implicitly makes use of those hyperlinks to expand entity candidates' descriptions and then compares them against the query context. Unfortunately, cross-document hyperlinks are rarely available in many closed domain knowledge bases and it is very expensive to manually add such links. Therefore few algorithms can work well on linkless knowledge bases. In this work, we propose the challenging Named Entity Disambiguation with Linkless Knowledge Bases (LNED) problem and tackle it by leveraging the useful disambiguation evidences scattered across the reference knowledge base. We propose a generative model to automatically mine such evidences out of noisy information. The mined evidences can mimic the role of the missing links and help boost the LNED performance. Experimental results show that our proposed method substantially improves the disambiguation accuracy over the baseline approaches.","PeriodicalId":20455,"journal":{"name":"Proceedings of the 25th International Conference on World Wide Web","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85338228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We investigate the moderating effect of product attributes and consumer reviews on the efficacy of a collaborative filtering recommender system on an e-commerce site. We run a randomized field experiment on a top North American retailer's website with 184,375 users split into a recommender-treated group and a control group with 37,215 unique products in the dataset. By augmenting the dataset with Amazon Mechanical Turk tagged product attributes and consumer review data from the website, we study their moderating influence on recommenders in generating conversion. We first confirm that the use of recommenders increases the baseline conversion rate by 5.9%. We find that the recommenders act as substitutes for high average review ratings with the effect of using recommenders increasing the conversion rate as much as about 1.4 additional average star ratings. Additionally, we find that the positive impacts on conversion from recommenders are greater for hedonic products compared to utilitarian products while search-experience quality did not have any impact. We also find that the higher the price, the lower the positive impact of recommenders, while having lengthier product descriptions and higher review volumes increased the recommender's effectiveness. More findings are discussed in the Results. For managers, we 1) identify the products and product attributes for which the recommenders work well, 2) show how other product information sources on e-commerce sites interact with recommenders. Additionally, the insights from the results could inform novel recommender algorithm designs that are aware of strength and shortcomings. From an academic standpoint, we provide insight into the underlying mechanism behind how recommenders cause consumers to purchase.
{"title":"When do Recommender Systems Work the Best?: The Moderating Effects of Product Attributes and Consumer Reviews on Recommender Performance","authors":"Dokyun Lee, K. Hosanagar","doi":"10.1145/2872427.2882976","DOIUrl":"https://doi.org/10.1145/2872427.2882976","url":null,"abstract":"We investigate the moderating effect of product attributes and consumer reviews on the efficacy of a collaborative filtering recommender system on an e-commerce site. We run a randomized field experiment on a top North American retailer's website with 184,375 users split into a recommender-treated group and a control group with 37,215 unique products in the dataset. By augmenting the dataset with Amazon Mechanical Turk tagged product attributes and consumer review data from the website, we study their moderating influence on recommenders in generating conversion. We first confirm that the use of recommenders increases the baseline conversion rate by 5.9%. We find that the recommenders act as substitutes for high average review ratings with the effect of using recommenders increasing the conversion rate as much as about 1.4 additional average star ratings. Additionally, we find that the positive impacts on conversion from recommenders are greater for hedonic products compared to utilitarian products while search-experience quality did not have any impact. We also find that the higher the price, the lower the positive impact of recommenders, while having lengthier product descriptions and higher review volumes increased the recommender's effectiveness. More findings are discussed in the Results. For managers, we 1) identify the products and product attributes for which the recommenders work well, 2) show how other product information sources on e-commerce sites interact with recommenders. Additionally, the insights from the results could inform novel recommender algorithm designs that are aware of strength and shortcomings. From an academic standpoint, we provide insight into the underlying mechanism behind how recommenders cause consumers to purchase.","PeriodicalId":20455,"journal":{"name":"Proceedings of the 25th International Conference on World Wide Web","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74660257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Beidou Wang, M. Ester, Jiajun Bu, Yu Zhu, Ziyu Guan, Deng Cai
Email is one of the most important communication tools today, but email overload resulting from the large number of unimportant or irrelevant emails is causing trillion-level economy loss every year. Thus personalized email prioritization algorithms are of urgent need. Despite lots of previous effort on this topic, broadcast email, an important type of email, is overlooked in previous literature. Broadcast emails are significantly different from normal emails, introducing both new challenges and opportunities. On one hand, lack of real senders and limited user interactions invalidate the key features exploited by traditional email prioritization algorithms; on the other hand, thousands of receivers for one broadcast email bring us the opportunity to predict importance through collaborative filtering. However, broadcast emails face a severe cold-start problem which hinders the direct application of collaborative filtering. In this paper, we propose the first framework for broadcast email prioritization by designing a novel active learning model that considers the collaborative filtering, implicit feedback and time sensitive responsiveness features of broadcast emails. Our method is thoroughly evaluated on a large scale real world industrial dataset from Samsung Electronics. Our method is proved highly effective and outperforms state-of-the-art personalized email prioritization methods.
{"title":"Which to View: Personalized Prioritization for Broadcast Emails","authors":"Beidou Wang, M. Ester, Jiajun Bu, Yu Zhu, Ziyu Guan, Deng Cai","doi":"10.1145/2872427.2883049","DOIUrl":"https://doi.org/10.1145/2872427.2883049","url":null,"abstract":"Email is one of the most important communication tools today, but email overload resulting from the large number of unimportant or irrelevant emails is causing trillion-level economy loss every year. Thus personalized email prioritization algorithms are of urgent need. Despite lots of previous effort on this topic, broadcast email, an important type of email, is overlooked in previous literature. Broadcast emails are significantly different from normal emails, introducing both new challenges and opportunities. On one hand, lack of real senders and limited user interactions invalidate the key features exploited by traditional email prioritization algorithms; on the other hand, thousands of receivers for one broadcast email bring us the opportunity to predict importance through collaborative filtering. However, broadcast emails face a severe cold-start problem which hinders the direct application of collaborative filtering. In this paper, we propose the first framework for broadcast email prioritization by designing a novel active learning model that considers the collaborative filtering, implicit feedback and time sensitive responsiveness features of broadcast emails. Our method is thoroughly evaluated on a large scale real world industrial dataset from Samsung Electronics. Our method is proved highly effective and outperforms state-of-the-art personalized email prioritization methods.","PeriodicalId":20455,"journal":{"name":"Proceedings of the 25th International Conference on World Wide Web","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89447225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kewen Liao, M. Petri, Alistair Moffat, Anthony Wirth
Web crawls generate vast quantities of text, retained and archived by the search services that initiate them. To store such data and to allow storage costs to be minimized, while still providing some level of random access to the compressed data, efficient and effective compression techniques are critical. The Relative Lempel Ziv (RLZ) scheme provides fast decompression and retrieval of documents from within large compressed collections, and even with a relatively small RAM-resident dictionary, is competitive relative to adaptive compression schemes. To date, the dictionaries required by RLZ compression have been formed from concatenations of substrings regularly sampled from the underlying document collection, then pruned in a manner that seeks to retain only the high-use sections. In this work, we develop new dictionary design heuristics, based on effective construction, rather than on pruning; we identify dictionary construction as a (string) covering problem. To avoid the complications of string covering algorithms on large collections, we focus on k-mers and their frequencies. First, with a reservoir sampler, we efficiently identify the most common k-mers. Then, since a collection typically comprises regions of local similarity, we select in each "epoch" a segment whose k-mers together achieve, locally, the highest coverage score. The dictionary is formed from the concatenation of these epoch-derived segments. Our selection process is inspired by the greedy approach to the Set Cover problem. Compared with the best existing pruning method, CARE, our scheme has a similar construction time, but achieves better compression effectiveness. Over several multi-gigabyte document collections, there are relative gains of up to 27%.
{"title":"Effective Construction of Relative Lempel-Ziv Dictionaries","authors":"Kewen Liao, M. Petri, Alistair Moffat, Anthony Wirth","doi":"10.1145/2872427.2883042","DOIUrl":"https://doi.org/10.1145/2872427.2883042","url":null,"abstract":"Web crawls generate vast quantities of text, retained and archived by the search services that initiate them. To store such data and to allow storage costs to be minimized, while still providing some level of random access to the compressed data, efficient and effective compression techniques are critical. The Relative Lempel Ziv (RLZ) scheme provides fast decompression and retrieval of documents from within large compressed collections, and even with a relatively small RAM-resident dictionary, is competitive relative to adaptive compression schemes. To date, the dictionaries required by RLZ compression have been formed from concatenations of substrings regularly sampled from the underlying document collection, then pruned in a manner that seeks to retain only the high-use sections. In this work, we develop new dictionary design heuristics, based on effective construction, rather than on pruning; we identify dictionary construction as a (string) covering problem. To avoid the complications of string covering algorithms on large collections, we focus on k-mers and their frequencies. First, with a reservoir sampler, we efficiently identify the most common k-mers. Then, since a collection typically comprises regions of local similarity, we select in each \"epoch\" a segment whose k-mers together achieve, locally, the highest coverage score. The dictionary is formed from the concatenation of these epoch-derived segments. Our selection process is inspired by the greedy approach to the Set Cover problem. Compared with the best existing pruning method, CARE, our scheme has a similar construction time, but achieves better compression effectiveness. Over several multi-gigabyte document collections, there are relative gains of up to 27%.","PeriodicalId":20455,"journal":{"name":"Proceedings of the 25th International Conference on World Wide Web","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87777961","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Online social networks regularly offer users personalized, algorithmic suggestions of whom to connect to. Here we examine the aggregate effects of such recommendations on network structure, focusing on whether these recommendations increase the popularity of niche users or, conversely, those who are already popular. We investigate this issue by empirically and theoretically analyzing abrupt changes in Twitter's network structure around the mid-2010 introduction of its "Who to Follow" feature. We find that users across the popularity spectrum benefitted from the recommendations; however, the most popular users profited substantially more than average. We trace this "rich get richer" phenomenon to three intertwined factors. First, as is typical of network recommenders, the system relies on a "friend-of-friend"-style algorithm, which we show generally results in users being recommended proportional to their degree. Second, we find that the baseline growth rate of users is sublinear in degree. This mismatch between the recommender and the natural network dynamics thus alters the structural evolution of the network. Finally, we find that people are much more likely to respond positively to recommendations for popular users---perhaps because of their greater name recognition---further amplifying the cumulative advantage of well-known individuals.
{"title":"The Effect of Recommendations on Network Structure","authors":"Jessica Su, Aneesh Sharma, Sharad Goel","doi":"10.1145/2872427.2883040","DOIUrl":"https://doi.org/10.1145/2872427.2883040","url":null,"abstract":"Online social networks regularly offer users personalized, algorithmic suggestions of whom to connect to. Here we examine the aggregate effects of such recommendations on network structure, focusing on whether these recommendations increase the popularity of niche users or, conversely, those who are already popular. We investigate this issue by empirically and theoretically analyzing abrupt changes in Twitter's network structure around the mid-2010 introduction of its \"Who to Follow\" feature. We find that users across the popularity spectrum benefitted from the recommendations; however, the most popular users profited substantially more than average. We trace this \"rich get richer\" phenomenon to three intertwined factors. First, as is typical of network recommenders, the system relies on a \"friend-of-friend\"-style algorithm, which we show generally results in users being recommended proportional to their degree. Second, we find that the baseline growth rate of users is sublinear in degree. This mismatch between the recommender and the natural network dynamics thus alters the structural evolution of the network. Finally, we find that people are much more likely to respond positively to recommendations for popular users---perhaps because of their greater name recognition---further amplifying the cumulative advantage of well-known individuals.","PeriodicalId":20455,"journal":{"name":"Proceedings of the 25th International Conference on World Wide Web","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86672106","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Instagram has more than 400 million monthly active accounts who share more than 80 million pictures and videos daily. This large volume of user-generated content is the application's notable strength, but also makes the problem of finding the authoritative users for a given topic challenging. Discovering topical authorities can be useful for providing relevant recommendations to the users. In addition, it can aid in building a catalog of topics and top topical authorities in order to engage new users, and hence provide a solution to the cold-start problem. In this paper, we present a novel approach that we call the Authority Learning Framework (ALF) to find topical authorities in Instagram. ALF is based on the self-described interests of the follower base of popular accounts. We infer regular users' interests from their self-reported biographies that are publicly available and use Wikipedia pages to ground these interests as fine-grained, disambiguated concepts. We propose a generalized label propagation algorithm to propagate the interests over the follower graph to the popular accounts. We show that even if biography-based interests are sparse at an individual user level they provide strong signals to infer the topical authorities and let us obtain a high precision authority list per topic. Our experiments demonstrate that ALF performs significantly better at user recommendation task compared to fine-tuned and competitive methods, via controlled experiments, in-the-wild tests, and over an expert-curated list of topical authorities.
{"title":"Discovery of Topical Authorities in Instagram","authors":"Aditya Pal, Amac Herdagdelen, Sourav Chatterji, Sumit Taank, Deepayan Chakrabarti","doi":"10.1145/2872427.2883078","DOIUrl":"https://doi.org/10.1145/2872427.2883078","url":null,"abstract":"Instagram has more than 400 million monthly active accounts who share more than 80 million pictures and videos daily. This large volume of user-generated content is the application's notable strength, but also makes the problem of finding the authoritative users for a given topic challenging. Discovering topical authorities can be useful for providing relevant recommendations to the users. In addition, it can aid in building a catalog of topics and top topical authorities in order to engage new users, and hence provide a solution to the cold-start problem. In this paper, we present a novel approach that we call the Authority Learning Framework (ALF) to find topical authorities in Instagram. ALF is based on the self-described interests of the follower base of popular accounts. We infer regular users' interests from their self-reported biographies that are publicly available and use Wikipedia pages to ground these interests as fine-grained, disambiguated concepts. We propose a generalized label propagation algorithm to propagate the interests over the follower graph to the popular accounts. We show that even if biography-based interests are sparse at an individual user level they provide strong signals to infer the topical authorities and let us obtain a high precision authority list per topic. Our experiments demonstrate that ALF performs significantly better at user recommendation task compared to fine-tuned and competitive methods, via controlled experiments, in-the-wild tests, and over an expert-curated list of topical authorities.","PeriodicalId":20455,"journal":{"name":"Proceedings of the 25th International Conference on World Wide Web","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86380766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Bin Liang, Miaoqiang Su, Wei You, Wenchang Shi, Gang Yang
Various classifiers based on the machine learning techniques have been widely used in security applications. Meanwhile, they also became an attack target of adversaries. Many existing studies have paid much attention to the evasion attacks on the online classifiers and discussed defensive methods. However, the security of the classifiers deployed in the client environment has not got the attention it deserves. Besides, earlier studies only concentrated on the experimental classifiers developed for research purposes only. The security of widely-used commercial classifiers still remains unclear. In this paper, we use the Google's phishing pages filter (GPPF), a classifier deployed in the Chrome browser which owns over one billion users, as a case to investigate the security challenges for the client-side classifiers. We present a new attack methodology targeting on client-side classifiers, called classifiers cracking. With the methodology, we successfully cracked the classification model of GPPF and extracted sufficient knowledge can be exploited for evasion attacks, including the classification algorithm, scoring rules and features, etc. Most importantly, we completely reverse engineered 84.8% scoring rules, covering most of high-weighted rules. Based on the cracked information, we performed two kinds of evasion attacks to GPPF, using 100 real phishing pages for the evaluation purpose. The experiments show that all the phishing pages (100%) can be easily manipulated to bypass the detection of GPPF. Our study demonstrates that the existing client-side classifiers are very vulnerable to classifiers cracking attacks.
{"title":"Cracking Classifiers for Evasion: A Case Study on the Google's Phishing Pages Filter","authors":"Bin Liang, Miaoqiang Su, Wei You, Wenchang Shi, Gang Yang","doi":"10.1145/2872427.2883060","DOIUrl":"https://doi.org/10.1145/2872427.2883060","url":null,"abstract":"Various classifiers based on the machine learning techniques have been widely used in security applications. Meanwhile, they also became an attack target of adversaries. Many existing studies have paid much attention to the evasion attacks on the online classifiers and discussed defensive methods. However, the security of the classifiers deployed in the client environment has not got the attention it deserves. Besides, earlier studies only concentrated on the experimental classifiers developed for research purposes only. The security of widely-used commercial classifiers still remains unclear. In this paper, we use the Google's phishing pages filter (GPPF), a classifier deployed in the Chrome browser which owns over one billion users, as a case to investigate the security challenges for the client-side classifiers. We present a new attack methodology targeting on client-side classifiers, called classifiers cracking. With the methodology, we successfully cracked the classification model of GPPF and extracted sufficient knowledge can be exploited for evasion attacks, including the classification algorithm, scoring rules and features, etc. Most importantly, we completely reverse engineered 84.8% scoring rules, covering most of high-weighted rules. Based on the cracked information, we performed two kinds of evasion attacks to GPPF, using 100 real phishing pages for the evaluation purpose. The experiments show that all the phishing pages (100%) can be easily manipulated to bypass the detection of GPPF. Our study demonstrates that the existing client-side classifiers are very vulnerable to classifiers cracking attacks.","PeriodicalId":20455,"journal":{"name":"Proceedings of the 25th International Conference on World Wide Web","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90142081","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Aspect-level sentiment analysis or opinion mining consists of several core sub-tasks: aspect extraction, opinion identification, polarity classification, and separation of general and aspect-specific opinions. Various topic models have been proposed by researchers to address some of these sub-tasks. However, there is little work on modeling all of them together. In this paper, we first propose a holistic fine-grained topic model, called the JAST (Joint Aspect-based Sentiment Topic) model, that can simultaneously model all of above problems under a unified framework. To further improve it, we incorporate the idea of lifelong machine learning and propose a more advanced model, called the LAST (Lifelong Aspect-based Sentiment Topic) model. LAST automatically mines the prior knowledge of aspect, opinion, and their correspondence from other products or domains. Such knowledge is automatically extracted and incorporated into the proposed LAST model without any human involvement. Our experiments using reviews of a large number of product domains show major improvements of the proposed models over state-of-the-art baselines.
{"title":"Mining Aspect-Specific Opinion using a Holistic Lifelong Topic Model","authors":"Shuai Wang, Zhiyuan Chen, Bing Liu","doi":"10.1145/2872427.2883086","DOIUrl":"https://doi.org/10.1145/2872427.2883086","url":null,"abstract":"Aspect-level sentiment analysis or opinion mining consists of several core sub-tasks: aspect extraction, opinion identification, polarity classification, and separation of general and aspect-specific opinions. Various topic models have been proposed by researchers to address some of these sub-tasks. However, there is little work on modeling all of them together. In this paper, we first propose a holistic fine-grained topic model, called the JAST (Joint Aspect-based Sentiment Topic) model, that can simultaneously model all of above problems under a unified framework. To further improve it, we incorporate the idea of lifelong machine learning and propose a more advanced model, called the LAST (Lifelong Aspect-based Sentiment Topic) model. LAST automatically mines the prior knowledge of aspect, opinion, and their correspondence from other products or domains. Such knowledge is automatically extracted and incorporated into the proposed LAST model without any human involvement. Our experiments using reviews of a large number of product domains show major improvements of the proposed models over state-of-the-art baselines.","PeriodicalId":20455,"journal":{"name":"Proceedings of the 25th International Conference on World Wide Web","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85140741","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：