System to Filter Unwanted Messages from OSN User Walls

System to Filter Unwanted Messages from OSN User Walls M.Renuga Devi, G.Seetha lakshmi, M.Sarmila Abstract—One fundamental issue in today’s Online Social Networks (OSNs) is to give users the ability to control the messages posted on their own private space to avoid that unwanted content is displayed. Up to now, OSNs provide little support to this requirement. To fill the gap, in this paper, we propose a system allowing OSN users to have a direct control on the messages posted on their walls. This is achieved through a flexible rule-based system, that allows users to customize the filtering criteria to be applied to their walls, and a Machine Learning-based soft classifier automatically labeling messages in support of content-based filtering. 1. INTRODUCTION ONLINE Social Networks (OSNs) are today one of the most popular interactive medium to communicate, share, and disseminate a considerable amount of human life information. Daily and continuous communications imply the exchange of several types of content, including free text, image, audio, and video data. According to Facebookstatistics1 average user creates 90 pieces of content each month, whereas more than 30 billion pieces of content (web links, news, stories, blog posts, notes, photo albums, etc.) are shared each month. OSNs there is the possibility of posting or commenting other posts on particular public/private areas, called in general walls. Face book allows users to state who is allowed to insert messages in their walls (i.e., friends, friends of friends, or defined groups of friends). The aim of the present work is therefore to propose and experimentally evaluate an automated system, called Filtered Wall (FW), able to filter unwanted messages from OSN user walls. We exploit Machine Learning (ML) text categorization techniques. The major efforts in building a robust short text classifier (STC) are concentrated in the extraction and selection of a set of characterizing and discriminant features. We base the overall short text classification strategy on Radial Basis Function Networks (RBFN) for their proven capabilities in acting as soft classifiers, in managing noisy data and intrinsically vague classes. We insert the neural model within a hierarchical two level classification strategy. In the first level, the RBFN categorizes short messages as Neutral and Non-neutral; in the second stage, Non-neutral messages are classified producing gradual estimates of appropriateness to each of the considered category. The system provides a powerful rule layer exploiting a flexible language to specify Filtering Rules (FRs). In addition, the system provides the support for user-defined Black Lists (BLs), that is, lists of users that are temporarily prevented to post any kind of messages on a user wall. 2. RELATED WORK The main contribution of this paper is the design of a system providing customizable content-based message filtering for OSNs, based on ML techniques. As we have pointed out in the introduction, to the best of our knowledge, we are the first proposing such kind of application for OSNs. However, our work has relationships both with the state of the art in content-based filtering, as well as with the field of policy-based personalization for OSNs and, more in general, web contents. 2.1 Content-Based Filtering Information filtering systems are designed to classify a stream of dynamically generated information dispatched asynchronously by an information producer and present to the user those information that are likely to satisfy his/her requirements. In content-based filtering, each user is assumed to operate independently. As a result, a content-based filtering system selects information items based on the correlation between the content of the items and the user preferences as opposed to a collaborative filtering system that chooses items based on the correlation between people with similar preferences. Documents processed in content-based filtering are mostly textual in nature and this makes content-based filtering close to text classification. Single label, binary classification, partitioning incoming documents into relevant and non-relevant categories. More complex filtering systems include multi label text categorization automatically labeling messages into partial thematic categories. Content-based filtering is mainly based on the use of the ML paradigm according to which a classifier is automatically induced by learning from a set of pre-classified examples. Several experiments prove that Bag-of-Words (BoW) approaches yield good performance and prevail in general over more sophisticated text representation that may have superior semantics but lower statistical quality. The application of content-based filtering on messages posted on OSN user walls poses additional challenges given the short length of these messages other than the wide range of topics that can be discussed. 3. FILTERED WALL ARCHITECTURE The architecture in support of OSN services is a three-tier structure (Fig. 1). The first layer, called Social Network Manager (SNM), commonly aims to provide the basic OSN functionalities (i.e., profile and relationship management), whereas the second layer provides the support for external Social Network Applications (SNAs).The supported SNAs may in turn require an additional layer for their needed Graphical User Interfaces (GUIs). The core components of the proposed system are the Content-Based Messages Filtering (CBMF) and the Short Text Classifier modules. The latter component aims to classify messages according to a set of categories. In contrast, the first component exploits the message categorization provided by the STC module to enforce the FRs specified by the user. The possible final publication can be summarized as follows: 1. After entering the private wall of one of his/her contacts, the user tries to post a message, which is intercepted by FW. 2. A ML-based text classifier extracts metadata from the content of the message. 3. FW uses metadata provided by the classifier, together with data extracted from the social graph and users’ profiles, to enforce the filtering and BL rules. 4. Depending on the result of the previous step, the message will be published or filtered by FW. 4. SHORT TEXT CLASSIFIER Established techniques used for text classification work well on data sets with large documents such as newswires corpora but suffer when the documents in the corpus are short. In this context, critical aspects are the definition of a set of characterizing and discriminant features allowing the representation of underlying concepts and the collection of a complete and consistent set of supervised examples. We approach the task by defining a hierarchical two-level strategy assuming that it is better to identify and eliminate â€Å"neutral† sentences, and then classify â€Å"non-neutral† sentences. The first-level task is conceived as a hard classification in which short texts are labeled with crisp Neutral and Non-neutral labels. The second-level soft classifier acts on the crisp set of non-neutral short texts. 4.1 Text Representation The extraction of an appropriate set of features by which representing the text of a given document is a crucial task strongly affecting the performance of the overall classification strategy. We consider three types of features, BoW, Document properties (Dp) and Contextual Features (CF). Text representation using endogenous knowledge has a good general applicability; however, in operational settings, it is legitimate to use also exogenous knowledge, i.e., any source of information outside the message body but directly or indirectly related to the message itself. We introduce CF modeling information that characterizes the environment where the user is posting. These features play a key role in deterministically understanding the semantics of the messages. In the BoW representation, terms are identified with words. Dp features are heuristically assessed; their definition stems from intuitive considerations, domain specific criteria and in some cases required trial-and-error procedures. Bad words: They are computed similarly to the correct words feature, where the set K is a collection of â€Å"dirty words† for the domain language. Correct words: It expresses the amount of terms tk 2 T K, where tk is a term of the considered document dj and K is a set of known words for the domain language. Capital words: It expresses the amount of words mostly written with capital letters, calculated as the percentage of words within the message, having more than half of the characters in capital case. Punctuations characters: It is calculated as the percentage of the punctuation characters over the total number of characters in the message. For example, the value of the feature for the document â€Å"Hello!!! How’re u doing?† is 5/24. Exclamation marks: It is calculated as the percentage of exclamation marks over the total number of punctuation characters in the message. Referring to the aforementioned document, the value is 3/5. Question marks: It is calculated as the percentage of question marks over the total number of punctuations characters in the message. Referring to the aforementioned document, the value is 1/5. 4.2 Machine Learning-Based Classification We address short text categorization as a hierarchical two level classification process. The first-level classifier performs a binary hard categorization that labels messages as Neutral and Non-neutral. The first-level filtering task facilitates the subsequent second-level task in which a finer-grained Classification is performed. The second-level classifier performs a soft-partition of Non-neutral messages assigning a given message a gradual membership to each of the non-neutral classes. Among the variety of multiclass ML models well suited for text classification, we choose the RBFN model for the experimented competitive behavior with respect to other state-of-the-art classifiers. RFBNs have a single hidden layer of processing units with local, restricted activation domain: a Gaussian function is commonly used, but any other locally tunable function can be used. RBFN main advantages are that classification function is nonlinear, the model may produce confidence values and it may be robust to outliers; drawbacks are the potential sensitivity to input parameters, and potential overtraining sensitivity. The first-level classifier is then structured as a regular RBFN. In the second level of the classification stage, we introduce a modification of the standard use of RBFN. The collection of pre-classified messages presents some critical aspects greatly affecting the performance of the overall classification strategy. To work well, a ML-based classifier needs to be trained with a set of sufficiently complete and consistent pre-classified data. The difficulty of satisfying this constraint is essentially related to the subjective character of the interpretation process with which an expert decides whether to classify a document under a given category. A quantitative evaluation of the agreement among experts is then developed to make transparent the level of inconsistency under which the classification process has taken place. 5. FILTERING RULES AND BLACKLIST MANAGEMENT In this section, we introduce the rule layer adopted for filtering unwanted messages. We start by describing FRs, and then we illustrate the use of BLs. In what follows, we model a social network as a directed graph, where each node corresponds to a network user and edges denote relationships between two different users. In particular, each edge is labeled by the type of the established relationship (e.g., friend of, colleague of, parent of) and, possibly, the corresponding trust level, which represents how much a given user considers trustworthy with respect to that specific kind of relationship the user with whom he/ she is establishing the relationship. 5.1 Filtering Rules In defining the language for FRs specification, we consider three main issues that, in our opinion, should affect a message filtering decision. First of all, in OSNs like in everyday life, the same message may have different meanings and relevance based on who writes it. As a consequence, FRs should allow users to state constraints on message creators. Given the social network Scenario, creators may also be identified by exploiting information on their social graph. Definition 1 (Creator specification): A creator specification creator Spec implicitly denotes a set of OSN users. It can have one of the following forms, possibly combined. Definition2 (Filtering rule): A filtering rule FR is a tuple (author, creator Spec, content Spec, action), where author is the user who specifies the rule; creator Spec is a creator specification, specified according to Definition 1: Content Spec is a Boolean expression defined on content constraints of the form à °C; mlÞ, where C is a class of the first or second level and ml is the minimum membership level threshold required for class C to make the constraint satisfied; action 2fblock; notifying denotes the action to be performed by the system on the messages matching content Spec and created by users identified by creator Spec. In general, more than a filtering rule can apply to the same user. A message is therefore published only if it is not blocked by any of the filtering rules that apply to the message creator. Note moreover, that it may happen that a user profile does not contain a value for the attribute(s) referred by a FR (e.g., the profile does not specify a value for the attribute Hometown whereas the FR blocks all the messages authored by users coming from a specific city). 5.2 Online Setup Assistant for FRs Thresholds As mentioned in the previous section, we address the problem of setting thresholds to filter rules, by conceiving and implementing within FW, an Online Setup Assistant procedure. 5.3 Blacklists A further component of our system is a BL mechanism to avoid messages from undesired creators, independent from their contents. BLs are directly managed by the system, which should be able to determine who are the users to be inserted in the BL and decide when users retention in the BL is finished. To enhance flexibility, such information are given to the system through a set of rules, hereafter called BL rules. Such rules are not defined by the SNMP; therefore, they are not meant as general high-level directives to be applied to the whole community. Similar to FRs, our BL rules make the wall owner able to identify users to be blocked according to their profiles as well as their relationships in the OSN. Therefore, by means of a BL rule, wall owners are, for example, able to ban from their walls users they do not directly know (i.e., with which they have only indirect relationships), or users that are friend of a given person as they may have a bad opinion of this person. 6. EVALUATION In this section, we illustrate the performance evaluation study we have carried out the classification and filtering modules. We start by describing the data set. 6.1 Problem and Data Set Description The analysis of related work has highlighted the lack of an publicly available benchmark for comparing different approaches to content-based classification of OSN short texts. 6.2 Short Text Classifier Evaluation 6.2.1 Evaluation Metrics Two different types of measures will be used to evaluate the effectiveness of first-level and second-level classifications. In the first level, the short text classification procedure is evaluated on the basis of the contingency table approach. In particular, the derived well-known Overall Accuracy (OA) index capturing the simple percent agreement between truth and classification results, is complemented with the Cohen’s KAPPA (K) coefficient thought to be a more robust measure taking into account the agreement occurring by chance . At second level, we adopt measures widely accepted in the Information Retrieval and Document Analysis field, that is, Precision (P), that permits to evaluate the number of false positives, Recall (R), that permits to evaluate the number of false negatives, and the overall metric F-Measure (F_), defined as the harmonic mean between the above two indexes. 6.2.2 Numerical Results By trial and error, we found a quite good parameter configuration for the RBFN learning model. The best value for the M parameter, that determines the number of Basis Function, is heuristically addressed to N=2, where N is the number of input patterns from the data set. 6.2.3 Comparison Analysis The lack of benchmarks for OSN short text classification makes problematic the development of a reliable comparative analysis. However, an indirect comparison of our method can be done with work that show similarities or complementary aspects with our solution. 6.3 Overall Performance and Discussion In order to provide an overall assessment of how effectively the system applies a FR. This table allows us to estimate the Precision and Recall of our FRs, Let us suppose that the system applies a given rule on a certain message. In contrast, Recall has to be interpreted as the probability that, given a rule that must be applied over a certain message, the rule is really enforced. Results achieved by the content-based specification component, on the first-level classification, can be considered good enough and reasonably aligned with those obtained by well-known information filtering techniques. 7. DICOMFw DicomFW is a prototype Face book application8 that emulates a personal wall where the user can apply a simple combination of the proposed FR’s. Throughout the development of the prototype, we have focused our attention only on the FRs, leaving BL implementation as a future improvement. However, the implemented functionality is critical, since it permits the STC and CBMF components to interact. To summarize, our application permits to 1. View the list of users’ FWs; 2. View messages and post a new one on a FW; 3. Define FRs using the OSA tool. When a user tries to post a message on a wall, he/ she receive an alerting message if it is blocked by FW. 8 CONCLUSIONS In this paper, we have presented a system to filter undesired messages from OSN walls. The system exploits a ML soft classifier to enforce customizable content-dependent FR’s. Fig. 3. DicomFW: A message filtered by the wall’s owner FRs We plan to study strategies and techniques limiting the inferences that a user can do on the enforced filtering rules with the aim of bypassing the filtering system, such as for instance randomly notifying a message that should instead be blocked, or detecting modifications to profile attributes that have been made for the only purpose of defeating the filtering system. REFERENCES [1] A. Adomavicius and G. Tuzhilin, â€Å"Toward the Next Generation of Recommender Systems: A Survey of the State-of-the-Art and Possible Extensions,† IEEE Trans. Knowledge and Data Eng., vol. 17, no. 6, pp. 734-749, June 2005. [2] M. Chua and H. Chen, â€Å"A Machine Learning Approach to Web Page Filtering Using Content and Structure Analysis,† Decision Support Systems, vol. 44, no. 2, pp. 482-494, 2008.

Organizational Citizenship Behavior

What is organizational citizenship behavior (OCB)? Describe in your own way. Organizational citizenship behavior (OCB) is behavior that goes beyond the basic requirements of the job, is to a large extent   left to one's own discretion, and is largely beneficial to the organization. OCB comes about as a result of job satisfaction. As employees that are highly satisfied with their jobs are more likely to think that they are being treated fairly , therefore trust in the organization and their employer is likely to arise . This then leads employee's to be more willing in helping out during extra hours voluntarily, volunteering for extra job activities, avoiding unnecessary conflict etc†¦ This is OCB. How is OCB different from normal working behavior? OCB is different from normal working behavior in the sense that the â€Å"employee goes out of his normal working behavior to get involved† (Allen, T. D. , 2006 ) into helping others and go beyond the normal expectations of their jobs. As a normal working behavior would be doing the tasks being asked of you and forced upon you as it is in your job description, but OCB differs from normal working behavior as â€Å"OCBs are employee behaviors that, although not critical to the task or job, serve to facilitate organizational functioning† (Lee and Allen, 2002, p 132). If you are a manager, how do you motivate your subordinates to exhibit more OCBs? Use the theories you have learned from different chapters. Firstly I would like to emphasize the importance of OCB to managers and the organization as a whole as successful organizations need employees who will do more than their usual job duties and provide performance that is beyond expectations and as I have mentioned before OCB describe actions in which employees are willing to go above and beyond their prescribed role requirements. Therefore reiterating the belief that these behaviors are correlated with indicators of organizational effectiveness, therefore showing us that OCB's are crucial for managers. Now, how to motivate subordinates to exhibit more OCB's, using Herzberg's two-factor theory that suggests that motivation factors (which include achievement, recognition, responsibility, growth, and work itself) are strongly related to job satisfaction. I can then say that if I was a manager I would have to make the jobs of my employees challenging, exciting , interesting and satisfying as employees who find their jobs to be such things, â€Å"tend to tolerate demanding supervision, avoid complaining, focus more on positive sides, and forgive organization’s minor faults. These kinds of behaviors are typically related to OCB. † (Herzberg et al. ’s 1959) Since hygiene factors are related to an individual’s job dissatisfaction, one can expect that hygiene factors may also influence an individual’s OCB. Therefore as a manager I would focus on placing hygiene factors such as job security, fringe benefits, and good work conditions so that dissatisfaction from the lack of these factors doesn't occur and OCB is therefore encouraged. Allen, T. D. (2006). Rewarding good citizens: The relationship between   citizenship behavior, gender, and organizational rewards. Journal of Applied Social Psychology, 36, 120-143. Lee, K. , & Allen, N. J. (2002). Organizational citizenship behavior and workplace deviance: The role of affect and cognitions. Journal of Applied Psychology, 87(1), 131-142. Herzberg, F. , Mausner, B. , & Snyderman, B. (1959). The motivation to work. New York: Wiley.

The Weather and Folklore of Altocumulus Clouds

An altocumulus cloud is a middle-level cloud that lives between 6,500 to 20,00 feet above ground and is made of water. Its name comes from the Latin Altus meaning high Cumulus meaning heaped. Altocumulus clouds are of the stratocumuliform cloud family (physical form) and are one of the 10 basic cloud types. There are four species of cloud underneath the altocumulus genus: altocumulus lenticularis (stationary lens-shaped clouds that are often mistaken for UFOs)altocumulus castellanus (altocumulus with tower-like sproutings that billow upwards)altocumulus stratiformis (altocumulus in sheets or relatively flat patches)altocumulus floccus (altocumulus with scattered tufts and fringy lower parts) The abbreviation for altocumulus clouds is (Ac). Cotton Balls in the Sky Altocumulus are commonly seen on warm spring and summer mornings. Theyre some of the simplest clouds to identify, especially since they look like balls of cotton stuck into the blue background of the sky. Theyre often white or gray in color and are arranged in patches of wavy, rounded masses or rolls. Altocumulus clouds are often called sheepback or mackerel sky because they resemble the wool of sheep and scales of mackerel fish. Bellwethers of Bad Weather Altocumulus clouds that appear on a clear humid morning can indicate the development of thunderstorms later in the day. Thats because altocumulus clouds often precede cold fronts of low-pressure systems. As such, they also sometimes signal the onset of cooler temperatures. While they are not clouds from which precipitation falls, their presence signals convection and instability at mid-levels of the troposphere. Altocumulus in Weather Folklore Mackerel sky, mackerel sky. Never long wet and never long dry.Mackerel scales and mares tails make lofty ships carry low sails. If youre a fan of weather folklore, youve likely heard the above sayings, both of which are true. The first piece of lore warns that if altocumulus clouds are seen and air pressure begins to fall, the weather wont be dry for much longer because it may start raining within 6 hours time. But once the rain does come, it wont be wet for long because as the warm front passes, so too will the precipitation. The second rhyme warns ships to lower and take in their sails for the same reason; a storm may be approaching soon and the sails should be lowered to protect them from the accompanying high winds.

Knowledge And Shows Emotional Intelligence Through...

Instills knowledge and shows emotional intelligence through humility. A successful manager must be able to balance practical knowledge with emotional intelligence. Professionalism - the expert knowledge, skills, and specific behavior that guide a worker (Batool, Khattak, Saleem, 2016) - must be paired with a clear understanding of behavioral knowledge. This assists the leader in rallying their employees to execute a shared vision. Within this framework, a characteristic that can enhance the effectiveness of a manager is humility. A contemporary view of humility may not immediately correlate with the decisive action and leading by example that is required to eliminate organizational obstacles to achieve desired goals. In fact, we often associate leaders with a higher status, and are generally viewed as more important than the average worker. However, research from Gà ¤chter et al (2012) shows that cooperative leaders contribute more to the group. Cooperation and leader humility is increasingly seen as important to organizational effectiveness (Owens Hekman, 2012). In an interview with Laura Suhr, a young branch manager of a local Honor Federal Credit Union, this trait was emphasized as a vital way for leaders to relate to staff and also remain accessible. Leader humility involves a leader modeling to her workers how to grow (L. Suhr, personal communication, October 7, 2016). This trait produces positive organizational outcomes by leading followers to believe that theirShow MoreRelatedWisdom Essay4887 Words   |  20 PagesProject Paper: Philosophy amp; Wisdom 1.0 INTRODUCTION Data is not information, Information is not knowledge, Knowledge is not understanding, Understanding is not wisdom. - Clifford Stoll - So what exactly is wisdom? Wisdom comes from the word ‘wise’, which means having or showing experience, knowledge, and good judgment . Did you know that the human race is also called homo sapien – which originated from Latin, meaning ‘wise’ or ‘knowing man’? This is simply due to the factRead MoreIs Education Means A Better Than Your Peers?991 Words   |  4 Pagesthe time to seek intelligence. For centuries this has been the case. From biblical times, to mid-evil times, to even modern times, it has been constantly argued what it means to be educated. Some believe that claiming education means hold certification. Others think that it means being able to communicate what you know or how you think. Ultimately, the author of this column, appearing in The Magnolia Potpourri on October 29th 2014, believes that sound judgment, mercy, and humility to be the marksRead MoreEssay Successful CEO Strategies966 Words   |  4 Pagessuccessful CEO knows how important it is for successful business leadership. Strong knowledge in accounting will help every CEO to understand much quicker business problems and opportunities that arise from the analysis of financial documents. A good base in accounting will also allow the CEO to communicate more effectively with the finance staff about company investments. It is never late to master the knowledge in accounting and every CEO should make sure that he or she is up to date with the accountingRead MoreLeadership Is A Fundamental Part Of The Non Profit Sector891 Words   |  4 Pagesability self-assessment, I ranked strongest in many areas of â€Å"Leaders Others† and â€Å"Produce Results†. My scores for the leadership skill â€Å"develops employees† were identified as a growth area. Understandably so, I generally do not have an opportunity to show this behavior on a regular basis. Although my job function requires coordination with other coworkers, I don’t manage other staff members. This is an area that I will look forward to gaining experience and professional growth in the future. ExperienceRead MoreThe Rise And Fall Of Carly Fiorina1641 Words   |  7 PagesMuch is made of the impact of leadership on an organisation. Theory has moved on from the idea of born leaders and specific traits that deliver effectiveness, to behavioural approaches and a distribution of the function through the organisation. ‘The Rise and Fall of Carly Fiorina’ (Johnson 2008) details Hewlett Packard’s recruitment of a celebrity CEO who took the organisation away from 60 years of distributed leadership, to implement an autocratic leadership style. This essay examines the caseRead MoreImpact of Emotional Intelligence on Leadership3981 Words   |  16 PagesTHE IMPACT OF EMOTIONAL INTELLIGENCE ON LEADERSHIP INTRODUCTION Our World today has more civilized societies with ever expanding population, having diversity in racial polarization, creed and gender. One common thread or feature in all these people is that everyone has feelings and emotions, and emotions engender emotional intelligence. We, being humans, are superior over other living creatures- we can think, feel and rationalize. Because of that we are being deluded by many behaviours, traitsRead MoreSocial Due Diligence And It Is Important For A Handful Of Reasons1055 Words   |  5 Pageslevel of understanding and acceptance. There is actually also a level of demonstrating mercy to the other person, as all judgment is placed aside. â€Å"Dialogue has the potential to unleash the wisdom and power latent in value conflicts and create the emotional will to create, problem solve, negotiate or lead others when cultural differences seem intractable.† (Putz, Schmitz Walch, p. 91). Cultural dialogue is incredibly important because it improves the team’s channel of communications and exchangeRead MoreTalking about Cultural Intelligence1887 Words   |  7 PagesWhen talking about cultural intelligence the first thing that comes to mind is the ability of culture, either individually or collectively, to interact with other cultures. Cultural intelligence does not refer to nationality, but rather to culture itself. And when talking about culture we are talking about values, attitudes, and beliefs shared by a group of people, when we talk about culture we also refer to organizational cultures, and other professionals that identify us with the groups they belongRead MoreNotes On Leaders And Leaders1632 Words   |  7 Pagesrequired work However, Kotter argues that leaders and managers approach those tasks differently: The leadership process involves a. Developing a vision for the organisation b. Aligning people with that vision through communication c. Motivating people to action through empowerment and through basic need fulfilment In contrast, the management process involves a. Planning and budgeting b. Organising and staffing c. Controlling and problem solving Both management and leadership are important for anRead MoreCareer As An Occupational Therapist Essay1952 Words   |  8 Pagesself-knowledge and the capability of being honest with oneself. Mueller understands his strengths, such as his level-headedness and ability to stay calm in conflict. However, he also recognizes his weaknesses, such as procrastination. His self-awareness allows him to work on what he struggles with, while utilizing his assets. In addition, Mueller remains honest in his work and strives to better himself through experiences. Of the five leadership traits identified by research, Mueller shows the most