Citation Context

...e [34] with the following features: • Unigram, bigram features with corresponding part-of-speech tags and NER labels. • Dictionary-derived features based on a subjectivity lexicon [90]. The CRF model =-=[43]-=- is trained using the CRF++ package6 based on the following features: • Current word, context words within a window of 3 words and their part-of-speech tags. • Name entity tags and corresponding POS t...

Citation Context

...ikes soccer (2) usrB explicitly mentions soccer in his or her posts. Satisfying both premises (especially the latter one) is a luxury. Inspired by common existing approaches to deal with missing data =-=[44, 51]-=-, we treat users’ LIKE/DISLIKE preferences as latent variables, while what is observed is whether users explicitly mention their preferences in their posts. The latent variables and observed variables...

Citation Context

...ollowing predicates hold: WORKIN(USR,ENTITY) (job), STUDY-AT(USR,ENTITY) (education) and SPOUSE(USR1,USR2) (spouse). Homophily: Our work is based on the fundamental homophily property of online users =-=[54]-=-, which assumes that people sharing logic form probability from MLN description FRIEND(A,B)∧ FRIEND(B,C)⇒ FRIEND(A,C) 0.082 friends of friends are friends COUPLE(A,B)∧ FRIEND(B,C)⇒ FRIEND(A,C) 0.127 o...

Citation Context

...for recommendations. The key idea of CF is to recommend similar items to similar users. We view the like/dislike entity prediction as entity recommendation problem and adopt the approach described in =-=[80]-=- by constructing user-user similarity matrix from weighted cosine similarity calculated from shared attributes and network information. Entity-entity similarity is computed based on entity embedding (...

Citation Context

...a source of supervision for data harvesting from raw text. Logic/Relational Reasoning: Logic reasoning, usually based on first-order logic representations, can be tracked back to the early days of AI =-=[59, 76]-=-, and has been adequately explored since then (e.g., [6, 14, 26, 32, 42, 45, 71, 72, 77, 81, 86, 87, 88, 89]). A variety of reasoning models have been proposed, based on ideas or concepts from the fie...

Citation Context

...cial relations must be inferred. We propose to infer user preferences on domains like Twitter without explicit information by applying relational reasoning frameworks like Markov Logic Networks (MLN) =-=[71]-=- and Probabilistic Soft Logic (PSL) [26] to help infer these relational rules. Such probabilistic logical systems are able to combine evidence probabilistically to draw logical inference. For example,...

Citation Context

...alization capabilities in terms of different types of data. Frameworks include Stochastic Logic Programs [61] which combines logic programming and log-linear models, Probabilistic Relational Networks =-=[23]-=- which incorporates Bayesian networks for reasoning, Relational Markov Networks [85] that uses dataset queries as cliques and model the state of clique in a Markov network, Relational Dependency Netwo...

Citation Context

... 42, 45, 71, 72, 77, 81, 86, 87, 88, 89]). A variety of reasoning models have been proposed, based on ideas or concepts from the fields of graphical models, relational logic, or programming languages =-=[7, 8, 60]-=-, each of which has it own generalization capabilities in terms of different types of data. Frameworks include Stochastic Logic Programs [61] which combines logic programming and log-linear models, Pr...

Citation Context

...ropose a text extraction system ar X iv :1 41 1. 26 79 v1s[ cs .SI ]s11sN ovs20 14 for Twitter that combines supervision [15], semi-supervised data harvesting (e.g., [40, 41]) and vector space models =-=[5, 55]-=- to automatically extract structured profiles from the text of users’ messages. Based on this approach, we are able to construct a comprehensive list of personal attributes which are explicitly mentio...

Citation Context

...astic Logic Programs [61] which combines logic programming and log-linear models, Probabilistic Relational Networks [23] which incorporates Bayesian networks for reasoning, Relational Markov Networks =-=[85]-=- that uses dataset queries as cliques and model the state of clique in a Markov network, Relational Dependency Networks [62] which combines Bayes networks and Markov networks, and probabilistic simila...

Citation Context

...make use of collaborative filtering, typically applied on structured data describing explicitly provided user preferences (e.g. movie ratings), and often enriched by information from a social network =-=[18, 25, 35, 38, 52]-=-. These methods can thus combine information from shared preferences and attributes with information about social relations. In many domains, however, these user preferences and user attributes are no...

Citation Context

...al structure. A great number of applications benefit from logical reasoning, including natural language understanding (e.g., [6]), health modeling [21], group modeling [29], web link based clustering =-=[22]-=-, object identification [20], trust analysis [30], and many more. 7. CONCLUSION AND DISCUSSION In this work, we propose a framework for applying probabilistic logical reasoning to inference problems o...

Citation Context

... the SVMlight package [34] with the following features: • Unigram, bigram features with corresponding part-of-speech tags and NER labels. • Dictionary-derived features based on a subjectivity lexicon =-=[90]-=-. The CRF model [43] is trained using the CRF++ package6 based on the following features: • Current word, context words within a window of 3 words and their part-of-speech tags. • Name entity tags and...

Citation Context

...ikes soccer (2) usrB explicitly mentions soccer in his or her posts. Satisfying both premises (especially the latter one) is a luxury. Inspired by common existing approaches to deal with missing data =-=[44, 51]-=-, we treat users’ LIKE/DISLIKE preferences as latent variables, while what is observed is whether users explicitly mention their preferences in their posts. The latent variables and observed variables...

Citation Context

...scenarios and forms. To deal with data sparsity issues, we collect training data by combining semi-supervised information harvesting techniques [16, 40, 41, 47] and the concept of distant supervision =-=[15, 24, 57]-=- as follows: Semi-supervised information harvesting: We applied the standard seed-based information-extraction method of obtaining training data recursively by using seed examples to extract patterns,...

Citation Context

...scenarios and forms. To deal with data sparsity issues, we collect training data by combining semi-supervised information harvesting techniques [16, 40, 41, 47] and the concept of distant supervision =-=[15, 24, 57]-=- as follows: Semi-supervised information harvesting: We applied the standard seed-based information-extraction method of obtaining training data recursively by using seed examples to extract patterns,...

Citation Context

...references and attitudes—a central focus of our work—and specifically the predicates LIKE(USR,ENTITY) and DISLIKE(USR,ENTITY). Like the large literature on sentiment analysis from social media (e.g., =-=[1, 39, 65, 79]-=-). our goal is to extract sentiment, but in addition to extract the target or object of the sentiment. Our work thus resembles other work on sentiment target extraction ([11, 36, 91]) using supervised...

Citation Context

...ropose a text extraction system ar X iv :1 41 1. 26 79 v1s[ cs .SI ]s11sN ovs20 14 for Twitter that combines supervision [15], semi-supervised data harvesting (e.g., [40, 41]) and vector space models =-=[5, 55]-=- to automatically extract structured profiles from the text of users’ messages. Based on this approach, we are able to construct a comprehensive list of personal attributes which are explicitly mentio...

Citation Context

...a source of supervision for data harvesting from raw text. Logic/Relational Reasoning: Logic reasoning, usually based on first-order logic representations, can be tracked back to the early days of AI =-=[59, 76]-=-, and has been adequately explored since then (e.g., [6, 14, 26, 32, 42, 45, 71, 72, 77, 81, 86, 87, 88, 89]). A variety of reasoning models have been proposed, based on ideas or concepts from the fie...

Citation Context

...cation Our goal is to associate one of the 50 states of the United States with each user. While there has been a significant amount of work on inferring the location of a given published tweet (e.g., =-=[10, 17, 78]-=-), there is less focus on user-level inference. In this paper, we employ a rule-based approach for user-location identification. We selected out all geo-tagged tweets from a specific user, and say an ...

Citation Context

...nal events [47] or individual attributes such as age [70, 69], gender [12], political polarity [13], locations [78], jobs and educations [48], student information (e.g., major, year of matriculation) =-=[58]-=-. The first step of proposed approach highly relies on attribute extraction algorithm described in [48] which extracts three categories of user attributes (i.g., education, job and spouse) for a given...

Citation Context

...ch incorporates Bayesian networks for reasoning, Relational Markov Networks [85] that uses dataset queries as cliques and model the state of clique in a Markov network, Relational Dependency Networks =-=[62]-=- which combines Bayes networks and Markov networks, and probabilistic similarity logic [7] which jointly considers probabilistic reasoning about similarities and relational structure. A great number o...

Citation Context

...references and attitudes—a central focus of our work—and specifically the predicates LIKE(USR,ENTITY) and DISLIKE(USR,ENTITY). Like the large literature on sentiment analysis from social media (e.g., =-=[1, 39, 65, 79]-=-). our goal is to extract sentiment, but in addition to extract the target or object of the sentiment. Our work thus resembles other work on sentiment target extraction ([11, 36, 91]) using supervised...

Citation Context

...e rest of the predicates is written as: P (li|lrest) = P (li ∧ lrest) P (lrest) = ∑ x∈li∪lrest P (x|·)∑ x∈lrest P (x|·) (3) Many approaches have been proposed for fast and effective learning for MLNs =-=[53, 63, 82]-=-. In this work, we use the discriminative training approach [82], as will be demonstrated in Section 4.1. 9Consecutive entities with same type of NER labels are merged. 10Word embedding dimension is s...

Citation Context

...een like and dislike5. • A token-level CRF sequence model (entity-model) to identify entities that are the target of the users like/dislike. The SVM classifiers are trained using the SVMlight package =-=[34]-=- with the following features: • Unigram, bigram features with corresponding part-of-speech tags and NER labels. • Dictionary-derived features based on a subjectivity lexicon [90]. The CRF model [43] i...

Citation Context

...make use of collaborative filtering, typically applied on structured data describing explicitly provided user preferences (e.g. movie ratings), and often enriched by information from a social network =-=[18, 25, 35, 38, 52]-=-. These methods can thus combine information from shared preferences and attributes with information about social relations. In many domains, however, these user preferences and user attributes are no...

Citation Context

... a brief illustration is shown in Figure 2. The conditional probability can be expressed by summing over latent variables. The system can be optimized by incorporating a form of EM algorithm into MLN =-=[83]-=-. For PSI, each entity is associated with an additional predicate MENTION (USR, ENTITY), denoting the situation where any given user publishes posts about one specific entity. Predicate PUBLISHENTITY(...

Citation Context

...s to use some seeds to harvest some data, which is used to learn additional rules or patterns to harvest more data [16, 31, 40, 41, 73]. Distant supervision is another methodology for data harvesting =-=[15, 28, 57]-=- that relies on structured data sources as a source of supervision for data harvesting from raw text. Logic/Relational Reasoning: Logic reasoning, usually based on first-order logic representations, c...

Citation Context

...l media (e.g., [1, 39, 65, 79]). our goal is to extract sentiment, but in addition to extract the target or object of the sentiment. Our work thus resembles other work on sentiment target extraction (=-=[11, 36, 91]-=-) using supervised classifiers or sequence models based on manually-labeled datasets. Unfortunately, manually collecting training data in this task is problematic because (1) tweets talking about what...

Citation Context

...e. Features include individual attributes values (e.g., like/dislike, location, gender, etc) and network information (attributes from his friends along the network) • Collaborative Filtering (CF): CF =-=[18, 25, 33, 35]-=- accounts for a popular approach in recommendation system, which utilizes the information of the user-item matrix for recommendations. The key idea of CF is to recommend similar items to similar users...

Citation Context

...ntity) is good/ terrific/ cool/ awesome/ fantastic", “(I think) (entity) is bad/terrible/awful suck/sucks". Entities extracted here should be nouns, which is determined by a Twitter-tuned POS package =-=[64]-=-. Based on the harvested examples from each iteration, we train 3 machine learning classifiers: 4http://www.ssa.gov/oact/babynames/names.zip • A tweet-level SVM classifier (tweet-model 1) to distingui...

Citation Context

...icult to optimize (especially since inference on MLN is hard) and existing algorithms may not able to scale up to the size of network we consider, we turn to a greedy approach inspired by recent work =-=[48, 68]-=-: attributes are initialized from the logic network based on given attributes where missing values are not considered. Then for each user along the network, we iteratively re-estimate their attributes...

Citation Context

...yfriend/Girlfriend: For the spouse relation, we again turn to Li et al.’s system [48]. For any two given Twitter users and their published contents, the system returns a score Sspouse in the range of =-=[0,1]-=- indicating how likely SPOUSE(USR1,USR2) relation is to hold. We use a threshold of 0.5 and then for any pair of users with a higher score than 0.5, we use a continuous variable to denote the confiden...

Citation Context

...e rest of the predicates is written as: P (li|lrest) = P (li ∧ lrest) P (lrest) = ∑ x∈li∪lrest P (x|·)∑ x∈lrest P (x|·) (3) Many approaches have been proposed for fast and effective learning for MLNs =-=[53, 63, 82]-=-. In this work, we use the discriminative training approach [82], as will be demonstrated in Section 4.1. 9Consecutive entities with same type of NER labels are merged. 10Word embedding dimension is s...

Citation Context

...l media (e.g., [1, 39, 65, 79]). our goal is to extract sentiment, but in addition to extract the target or object of the sentiment. Our work thus resembles other work on sentiment target extraction (=-=[11, 36, 91]-=-) using supervised classifiers or sequence models based on manually-labeled datasets. Unfortunately, manually collecting training data in this task is problematic because (1) tweets talking about what...

Citation Context

...tracking [67] or event-referring expression extraction [74]. The latter focus on user studies, examining users’ interests [3], timeline [46], personal events [47] or individual attributes such as age =-=[70, 69]-=-, gender [12], political polarity [13], locations [78], jobs and educations [48], student information (e.g., major, year of matriculation) [58]. The first step of proposed approach highly relies on at...

Citation Context

...gic/Relational Reasoning: Logic reasoning, usually based on first-order logic representations, can be tracked back to the early days of AI [59, 76], and has been adequately explored since then (e.g., =-=[6, 14, 26, 32, 42, 45, 71, 72, 77, 81, 86, 87, 88, 89]-=-). A variety of reasoning models have been proposed, based on ideas or concepts from the fields of graphical models, relational logic, or programming languages [7, 8, 60], each of which has it own gen...

Citation Context

...n extraction [74]. The latter focus on user studies, examining users’ interests [3], timeline [46], personal events [47] or individual attributes such as age [70, 69], gender [12], political polarity =-=[13]-=-, locations [78], jobs and educations [48], student information (e.g., major, year of matriculation) [58]. The first step of proposed approach highly relies on attribute extraction algorithm described...

Citation Context

...again low-recall: another 0.5 percent of users’ job or education attributes are inferred from the system. 2.2.3 Gender Many frameworks have been devoted to gender prediction from Twitter posts (e.g., =-=[9, 12, 66, 84]-=-) studying whether high level tweet features (e.g., link, mention, hashtag frequency) can help in the absence of highly-predictive user name information. Since our 1Due to API limitations, we can craw...

Citation Context

...cation Our goal is to associate one of the 50 states of the United States with each user. While there has been a significant amount of work on inferring the location of a given published tweet (e.g., =-=[10, 17, 78]-=-), there is less focus on user-level inference. In this paper, we employ a rule-based approach for user-location identification. We selected out all geo-tagged tweets from a specific user, and say an ...

Citation Context

...gic/Relational Reasoning: Logic reasoning, usually based on first-order logic representations, can be tracked back to the early days of AI [59, 76], and has been adequately explored since then (e.g., =-=[6, 14, 26, 32, 42, 45, 71, 72, 77, 81, 86, 87, 88, 89]-=-). A variety of reasoning models have been proposed, based on ideas or concepts from the fields of graphical models, relational logic, or programming languages [7, 8, 60], each of which has it own gen...

Citation Context

...again low-recall: another 0.5 percent of users’ job or education attributes are inferred from the system. 2.2.3 Gender Many frameworks have been devoted to gender prediction from Twitter posts (e.g., =-=[9, 12, 66, 84]-=-) studying whether high level tweet features (e.g., link, mention, hashtag frequency) can help in the absence of highly-predictive user name information. Since our 1Due to API limitations, we can craw...

Citation Context

... of applications benefit from logical reasoning, including natural language understanding (e.g., [6]), health modeling [21], group modeling [29], web link based clustering [22], object identification =-=[20]-=-, trust analysis [30], and many more. 7. CONCLUSION AND DISCUSSION In this work, we propose a framework for applying probabilistic logical reasoning to inference problems on on social networks. Our tw...

Citation Context

...gic/Relational Reasoning: Logic reasoning, usually based on first-order logic representations, can be tracked back to the early days of AI [59, 76], and has been adequately explored since then (e.g., =-=[6, 14, 26, 32, 42, 45, 71, 72, 77, 81, 86, 87, 88, 89]-=-). A variety of reasoning models have been proposed, based on ideas or concepts from the fields of graphical models, relational logic, or programming languages [7, 8, 60], each of which has it own gen...

Citation Context

...gic/Relational Reasoning: Logic reasoning, usually based on first-order logic representations, can be tracked back to the early days of AI [59, 76], and has been adequately explored since then (e.g., =-=[6, 14, 26, 32, 42, 45, 71, 72, 77, 81, 86, 87, 88, 89]-=-). A variety of reasoning models have been proposed, based on ideas or concepts from the fields of graphical models, relational logic, or programming languages [7, 8, 60], each of which has it own gen...

Citation Context

...e rest of the predicates is written as: P (li|lrest) = P (li ∧ lrest) P (lrest) = ∑ x∈li∪lrest P (x|·)∑ x∈lrest P (x|·) (3) Many approaches have been proposed for fast and effective learning for MLNs =-=[53, 63, 82]-=-. In this work, we use the discriminative training approach [82], as will be demonstrated in Section 4.1. 9Consecutive entities with same type of NER labels are merged. 10Word embedding dimension is s...

Citation Context

...gic/Relational Reasoning: Logic reasoning, usually based on first-order logic representations, can be tracked back to the early days of AI [59, 76], and has been adequately explored since then (e.g., =-=[6, 14, 26, 32, 42, 45, 71, 72, 77, 81, 86, 87, 88, 89]-=-). A variety of reasoning models have been proposed, based on ideas or concepts from the fields of graphical models, relational logic, or programming languages [7, 8, 60], each of which has it own gen...

Citation Context

...tities into different groups, with an goal of answering questions like ‘if usr1 likes films, how likely would she like the film Titanic?’ Towards this goal, we train a skip-gram neural language model =-=[55, 56]-=- based on the tweet dataset using word2vec where each word is represented as a real-valued, low-dimensional vector10. Skipgram language models draw on local context in order to learn similar embedding...

Citation Context

...ds in social media15, and that friends (or couples, or people living in the same location) tend to share more attributes. Such properties have been harnessed for applications like community detection =-=[92]-=- or friend recommendation [27]. Data Harvesting: The techniques adopted in like/dislike attribute extraction are related to a strand of work in data harvesting/information extraction, the point of whi...

Citation Context

...references and attitudes—a central focus of our work—and specifically the predicates LIKE(USR,ENTITY) and DISLIKE(USR,ENTITY). Like the large literature on sentiment analysis from social media (e.g., =-=[1, 39, 65, 79]-=-). our goal is to extract sentiment, but in addition to extract the target or object of the sentiment. Our work thus resembles other work on sentiment target extraction ([11, 36, 91]) using supervised...

Citation Context

...melocation), and user preferences (liking or disliking different entities). Our results show that using probabilistic logical reasoning 15summarized by the proverb “birds of a feather flock together" =-=[2]-=-. over the network improves the accuracy of the resulting predictings, demonstrating the effectiveness of the proposed framework. Of course the current system is particularly weak in recall, since man...

Citation Context

...raction on Social Media : Much work has been devoted to automatic extraction of well-structured information profiles from online social media, which mainly fall into two major levels: at public level =-=[49, 50, 90]-=- or at user level. The former includes public event identification [19], event tracking [67] or event-referring expression extraction [74]. The latter focus on user studies, examining users’ interests...

Citation Context

...make use of collaborative filtering, typically applied on structured data describing explicitly provided user preferences (e.g. movie ratings), and often enriched by information from a social network =-=[18, 25, 35, 38, 52]-=-. These methods can thus combine information from shared preferences and attributes with information about social relations. In many domains, however, these user preferences and user attributes are no...

Citation Context

... friends (or couples, or people living in the same location) tend to share more attributes. Such properties have been harnessed for applications like community detection [92] or friend recommendation =-=[27]-=-. Data Harvesting: The techniques adopted in like/dislike attribute extraction are related to a strand of work in data harvesting/information extraction, the point of which is to use some seeds to har...

Citation Context

...raining approach [82], as will be demonstrated in Section 4.1. 9Consecutive entities with same type of NER labels are merged. 10Word embedding dimension is set to 200 3.2 Probabilistic Soft Logic PSL =-=[4, 37]-=- is another sort of logic reasoning architecture. It first associates each predicate l with a soft truth value I(l). Based on such soft truth values, PSL performs logical conjunction and disjunction i...

Citation Context

...make use of collaborative filtering, typically applied on structured data describing explicitly provided user preferences (e.g. movie ratings), and often enriched by information from a social network =-=[18, 25, 35, 38, 52]-=-. These methods can thus combine information from shared preferences and attributes with information about social relations. In many domains, however, these user preferences and user attributes are no...

Citation Context

...raction on Social Media : Much work has been devoted to automatic extraction of well-structured information profiles from online social media, which mainly fall into two major levels: at public level =-=[49, 50, 90]-=- or at user level. The former includes public event identification [19], event tracking [67] or event-referring expression extraction [74]. The latter focus on user studies, examining users’ interests...

Citation Context

...ressing what the user LIKES exist in a great variety of scenarios and forms. To deal with data sparsity issues, we collect training data by combining semi-supervised information harvesting techniques =-=[16, 40, 41, 47]-=- and the concept of distant supervision [15, 24, 57] as follows: Semi-supervised information harvesting: We applied the standard seed-based information-extraction method of obtaining training data rec...

Citation Context

... well-structured information profiles from online social media, which mainly fall into two major levels: at public level [49, 50, 90] or at user level. The former includes public event identification =-=[19]-=-, event tracking [67] or event-referring expression extraction [74]. The latter focus on user studies, examining users’ interests [3], timeline [46], personal events [47] or individual attributes such...

Citation Context

...gic/Relational Reasoning: Logic reasoning, usually based on first-order logic representations, can be tracked back to the early days of AI [59, 76], and has been adequately explored since then (e.g., =-=[6, 14, 26, 32, 42, 45, 71, 72, 77, 81, 86, 87, 88, 89]-=-). A variety of reasoning models have been proposed, based on ideas or concepts from the fields of graphical models, relational logic, or programming languages [7, 8, 60], each of which has it own gen...

Citation Context

...com/p/crfpp/ 7For example, if datasets says relation ISCAPITAL holds between Britain and London, then all sentences with mention of “Britain" and “London" are treated as expressing ISCAPITAL relation =-=[57, 75]-=-. 8Tweets with happy emoticons such as :-) : ) are of positive sentiment [24]. Stopping Condition: To decide the optimum number of steps for the algorithm to stop, we manually labeled a dataset which ...

Citation Context

...gic/Relational Reasoning: Logic reasoning, usually based on first-order logic representations, can be tracked back to the early days of AI [59, 76], and has been adequately explored since then (e.g., =-=[6, 14, 26, 32, 42, 45, 71, 72, 77, 81, 86, 87, 88, 89]-=-). A variety of reasoning models have been proposed, based on ideas or concepts from the fields of graphical models, relational logic, or programming languages [7, 8, 60], each of which has it own gen...

Citation Context

... RELIGION, or EDUCATION [48]. We propose a text extraction system ar X iv :1 41 1. 26 79 v1s[ cs .SI ]s11sN ovs20 14 for Twitter that combines supervision [15], semi-supervised data harvesting (e.g., =-=[40, 41]-=-) and vector space models [5, 55] to automatically extract structured profiles from the text of users’ messages. Based on this approach, we are able to construct a comprehensive list of personal attri...

Citation Context

... RELIGION, or EDUCATION [48]. We propose a text extraction system ar X iv :1 41 1. 26 79 v1s[ cs .SI ]s11sN ovs20 14 for Twitter that combines supervision [15], semi-supervised data harvesting (e.g., =-=[40, 41]-=-) and vector space models [5, 55] to automatically extract structured profiles from the text of users’ messages. Based on this approach, we are able to construct a comprehensive list of personal attri...

Citation Context

...rmation profiles from online social media, which mainly fall into two major levels: at public level [49, 50, 90] or at user level. The former includes public event identification [19], event tracking =-=[67]-=- or event-referring expression extraction [74]. The latter focus on user studies, examining users’ interests [3], timeline [46], personal events [47] or individual attributes such as age [70, 69], gen...

Citation Context

...gic/Relational Reasoning: Logic reasoning, usually based on first-order logic representations, can be tracked back to the early days of AI [59, 76], and has been adequately explored since then (e.g., =-=[6, 14, 26, 32, 42, 45, 71, 72, 77, 81, 86, 87, 88, 89]-=-). A variety of reasoning models have been proposed, based on ideas or concepts from the fields of graphical models, relational logic, or programming languages [7, 8, 60], each of which has it own gen...

Citation Context

...l media (e.g., [1, 39, 65, 79]). our goal is to extract sentiment, but in addition to extract the target or object of the sentiment. Our work thus resembles other work on sentiment target extraction (=-=[11, 36, 91]-=-) using supervised classifiers or sequence models based on manually-labeled datasets. Unfortunately, manually collecting training data in this task is problematic because (1) tweets talking about what...

Citation Context

...again low-recall: another 0.5 percent of users’ job or education attributes are inferred from the system. 2.2.3 Gender Many frameworks have been devoted to gender prediction from Twitter posts (e.g., =-=[9, 12, 66, 84]-=-) studying whether high level tweet features (e.g., link, mention, hashtag frequency) can help in the absence of highly-predictive user name information. Since our 1Due to API limitations, we can craw...

Citation Context

...tracking [67] or event-referring expression extraction [74]. The latter focus on user studies, examining users’ interests [3], timeline [46], personal events [47] or individual attributes such as age =-=[70, 69]-=-, gender [12], political polarity [13], locations [78], jobs and educations [48], student information (e.g., major, year of matriculation) [58]. The first step of proposed approach highly relies on at...

Citation Context

...ose to infer user preferences on domains like Twitter without explicit information by applying relational reasoning frameworks like Markov Logic Networks (MLN) [71] and Probabilistic Soft Logic (PSL) =-=[26]-=- to help infer these relational rules. Such probabilistic logical systems are able to combine evidence probabilistically to draw logical inference. For example, such systems could learn individual pro...

Citation Context

...or at user level. The former includes public event identification [19], event tracking [67] or event-referring expression extraction [74]. The latter focus on user studies, examining users’ interests =-=[3]-=-, timeline [46], personal events [47] or individual attributes such as age [70, 69], gender [12], political polarity [13], locations [78], jobs and educations [48], student information (e.g., major, y...

Citation Context

...again low-recall: another 0.5 percent of users’ job or education attributes are inferred from the system. 2.2.3 Gender Many frameworks have been devoted to gender prediction from Twitter posts (e.g., =-=[9, 12, 66, 84]-=-) studying whether high level tweet features (e.g., link, mention, hashtag frequency) can help in the absence of highly-predictive user name information. Since our 1Due to API limitations, we can craw...

Citation Context

...el. The former includes public event identification [19], event tracking [67] or event-referring expression extraction [74]. The latter focus on user studies, examining users’ interests [3], timeline =-=[46]-=-, personal events [47] or individual attributes such as age [70, 69], gender [12], political polarity [13], locations [78], jobs and educations [48], student information (e.g., major, year of matricul...

Citation Context

...raining approach [82], as will be demonstrated in Section 4.1. 9Consecutive entities with same type of NER labels are merged. 10Word embedding dimension is set to 200 3.2 Probabilistic Soft Logic PSL =-=[4, 37]-=- is another sort of logic reasoning architecture. It first associates each predicate l with a soft truth value I(l). Based on such soft truth values, PSL performs logical conjunction and disjunction i...

Citation Context

...d to a strand of work in data harvesting/information extraction, the point of which is to use some seeds to harvest some data, which is used to learn additional rules or patterns to harvest more data =-=[16, 31, 40, 41, 73]-=-. Distant supervision is another methodology for data harvesting [15, 28, 57] that relies on structured data sources as a source of supervision for data harvesting from raw text. Logic/Relational Reas...

Citation Context

...ch mainly fall into two major levels: at public level [49, 50, 90] or at user level. The former includes public event identification [19], event tracking [67] or event-referring expression extraction =-=[74]-=-. The latter focus on user studies, examining users’ interests [3], timeline [46], personal events [47] or individual attributes such as age [70, 69], gender [12], political polarity [13], locations [...

Citation Context

... the other hand, users of online social media frequently publish messages describing their preferences and activities, often explicitly mentioning attributes such as their JOB, RELIGION, or EDUCATION =-=[48]-=-. We propose a text extraction system ar X iv :1 41 1. 26 79 v1s[ cs .SI ]s11sN ovs20 14 for Twitter that combines supervision [15], semi-supervised data harvesting (e.g., [40, 41]) and vector space m...

Citation Context

...gic/Relational Reasoning: Logic reasoning, usually based on first-order logic representations, can be tracked back to the early days of AI [59, 76], and has been adequately explored since then (e.g., =-=[6, 14, 26, 32, 42, 45, 71, 72, 77, 81, 86, 87, 88, 89]-=-). A variety of reasoning models have been proposed, based on ideas or concepts from the fields of graphical models, relational logic, or programming languages [7, 8, 60], each of which has it own gen...

Citation Context

... 42, 45, 71, 72, 77, 81, 86, 87, 88, 89]). A variety of reasoning models have been proposed, based on ideas or concepts from the fields of graphical models, relational logic, or programming languages =-=[7, 8, 60]-=-, each of which has it own generalization capabilities in terms of different types of data. Frameworks include Stochastic Logic Programs [61] which combines logic programming and log-linear models, Pr...

Citation Context

... 42, 45, 71, 72, 77, 81, 86, 87, 88, 89]). A variety of reasoning models have been proposed, based on ideas or concepts from the fields of graphical models, relational logic, or programming languages =-=[7, 8, 60]-=-, each of which has it own generalization capabilities in terms of different types of data. Frameworks include Stochastic Logic Programs [61] which combines logic programming and log-linear models, Pr...

Citation Context

...obabilistic reasoning about similarities and relational structure. A great number of applications benefit from logical reasoning, including natural language understanding (e.g., [6]), health modeling =-=[21]-=-, group modeling [29], web link based clustering [22], object identification [20], trust analysis [30], and many more. 7. CONCLUSION AND DISCUSSION In this work, we propose a framework for applying pr...

Citation Context

... about similarities and relational structure. A great number of applications benefit from logical reasoning, including natural language understanding (e.g., [6]), health modeling [21], group modeling =-=[29]-=-, web link based clustering [22], object identification [20], trust analysis [30], and many more. 7. CONCLUSION AND DISCUSSION In this work, we propose a framework for applying probabilistic logical r...

Citation Context

...fit from logical reasoning, including natural language understanding (e.g., [6]), health modeling [21], group modeling [29], web link based clustering [22], object identification [20], trust analysis =-=[30]-=-, and many more. 7. CONCLUSION AND DISCUSSION In this work, we propose a framework for applying probabilistic logical reasoning to inference problems on on social networks. Our two-step procedure firs...

Citation Context

...ressing what the user LIKES exist in a great variety of scenarios and forms. To deal with data sparsity issues, we collect training data by combining semi-supervised information harvesting techniques =-=[16, 40, 41, 47]-=- and the concept of distant supervision [15, 24, 57] as follows: Semi-supervised information harvesting: We applied the standard seed-based information-extraction method of obtaining training data rec...

Citation Context

...gic/Relational Reasoning: Logic reasoning, usually based on first-order logic representations, can be tracked back to the early days of AI [59, 76], and has been adequately explored since then (e.g., =-=[6, 14, 26, 32, 42, 45, 71, 72, 77, 81, 86, 87, 88, 89]-=-). A variety of reasoning models have been proposed, based on ideas or concepts from the fields of graphical models, relational logic, or programming languages [7, 8, 60], each of which has it own gen...

Citation Context

...itly mentioning attributes such as their JOB, RELIGION, or EDUCATION [48]. We propose a text extraction system ar X iv :1 41 1. 26 79 v1s[ cs .SI ]s11sN ovs20 14 for Twitter that combines supervision =-=[15]-=-, semi-supervised data harvesting (e.g., [40, 41]) and vector space models [5, 55] to automatically extract structured profiles from the text of users’ messages. Based on this approach, we are able to...

Citation Context

...cation Our goal is to associate one of the 50 states of the United States with each user. While there has been a significant amount of work on inferring the location of a given published tweet (e.g., =-=[10, 17, 78]-=-), there is less focus on user-level inference. In this paper, we employ a rule-based approach for user-location identification. We selected out all geo-tagged tweets from a specific user, and say an ...

Citation Context

...d to a strand of work in data harvesting/information extraction, the point of which is to use some seeds to harvest some data, which is used to learn additional rules or patterns to harvest more data =-=[16, 31, 40, 41, 73]-=-. Distant supervision is another methodology for data harvesting [15, 28, 57] that relies on structured data sources as a source of supervision for data harvesting from raw text. Logic/Relational Reas...

Citation Context

...gic/Relational Reasoning: Logic reasoning, usually based on first-order logic representations, can be tracked back to the early days of AI [59, 76], and has been adequately explored since then (e.g., =-=[6, 14, 26, 32, 42, 45, 71, 72, 77, 81, 86, 87, 88, 89]-=-). A variety of reasoning models have been proposed, based on ideas or concepts from the fields of graphical models, relational logic, or programming languages [7, 8, 60], each of which has it own gen...

Citation Context

...make use of collaborative filtering, typically applied on structured data describing explicitly provided user preferences (e.g. movie ratings), and often enriched by information from a social network =-=[18, 25, 35, 38, 52]-=-. These methods can thus combine information from shared preferences and attributes with information about social relations. In many domains, however, these user preferences and user attributes are no...

Citation Context

...l models, relational logic, or programming languages [7, 8, 60], each of which has it own generalization capabilities in terms of different types of data. Frameworks include Stochastic Logic Programs =-=[61]-=- which combines logic programming and log-linear models, Probabilistic Relational Networks [23] which incorporates Bayesian networks for reasoning, Relational Markov Networks [85] that uses dataset qu...

Citation Context

...gic/Relational Reasoning: Logic reasoning, usually based on first-order logic representations, can be tracked back to the early days of AI [59, 76], and has been adequately explored since then (e.g., =-=[6, 14, 26, 32, 42, 45, 71, 72, 77, 81, 86, 87, 88, 89]-=-). A variety of reasoning models have been proposed, based on ideas or concepts from the fields of graphical models, relational logic, or programming languages [7, 8, 60], each of which has it own gen...